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

    Neuronpedia

    INDEX
    Explanations

    beginning of a text

    np_max-act · gemini-2.0-flash

    The neuron specifically activates on the word “let” (e.g. in “let the…” or “let’s…”), detecting that exact verb form.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    820
    -0.07
     adolescents
    -0.06
     Pun
    -0.06
    _comment
    -0.06
    ibold
    -0.06
    */}↵
    -0.06
    urve
    -0.06
    ERC
    -0.06
     doping
    -0.06
     setting
    -0.06
    POSITIVE LOGITS
     GetName
    0.07
     Brow
    0.07
     resolved
    0.07
     dataIndex
    0.07
     Elem
    0.06
    IFIER
    0.06
    となる
    0.06
     مشکل
    0.06
    _needed
    0.06
     Cush
    0.06
    Act Density 0.018%

    No Known Activations