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

    Neuronpedia

    INDEX
    Explanations

    String

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .mm
    -0.07
     bou
    -0.06
     Actors
    -0.06
    人员
    -0.06
    _npc
    -0.06
    "My
    -0.06
     strokeLine
    -0.06
    appointment
    -0.06
    絡
    -0.06
    Contracts
    -0.06
    POSITIVE LOGITS
     PLEASE
    0.07
    (/[
    0.07
    овая
    0.07
    books
    0.06
    овые
    0.06
    contentType
    0.06
    ست
    0.06
    atcher
    0.06
     Clip
    0.06
    -Le
    0.06
    Act Density 0.010%

    No Known Activations