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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    兵
    -0.07
     admon
    -0.06
    幹線
    -0.06
     lider
    -0.06
     언어
    -0.06
    .CR
    -0.06
    _contact
    -0.06
    弗
    -0.06
    _with
    -0.06
     Parcelable
    -0.06
    POSITIVE LOGITS
     Log
    0.06
    cht
    0.06
     Meet
    0.06
    ož
    0.06
    .req
    0.06
     cigaret
    0.06
     दस
    0.06
    /admin
    0.06
    ':['
    0.06
     stained
    0.06
    Act Density 0.019%

    No Known Activations