Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Unstructured mixed content

    np_max-act · gemini-2.0-flash

    The neuron responds to structural list and heading markers—i.e. tokens that introduce section titles, bullet/numbered list items, or enumerated metadata.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    details about real estate investments and their financing options.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ंस
    -0.07
     Mal
    -0.07
     induced
    -0.07
    ybrid
    -0.07
    .visibility
    -0.07
     invest
    -0.07
     polarity
    -0.07
     Conv
    -0.07
     pocket
    -0.07
    uron
    -0.06
    POSITIVE LOGITS
     보
    0.07
     �
    0.06
     fotoğraf
    0.06
    خانه
    0.06
     Cosby
    0.06
     Peb
    0.06
     اصفه
    0.06
    ้องน
    0.06
     北
    0.06
     ніби
    0.06
    Act Density 0.044%

    No Known Activations