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

    Neuronpedia

    INDEX
    Explanations

    ://

    np_max-act · gemini-2.0-flash

    The neuron activates on HTTP URLs (e.g. “http://www.boost.org/...”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �
    -0.07
    (mail
    -0.07
    Precio
    -0.06
    EMENT
    -0.06
    Pane
    -0.06
    يلاد
    -0.06
     eder
    -0.06
    -half
    -0.06
     Rogue
    -0.06
     ödem
    -0.06
    POSITIVE LOGITS
     overd
    0.07
     purposely
    0.06
    ักเร
    0.06
     binnen
    0.06
     coraz
    0.06
     şu
    0.06
    iero
    0.06
    DataAdapter
    0.06
    <k
    0.06
    ,response
    0.06
    Act Density 0.002%

    No Known Activations