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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Transform
    -0.07
     cộng
    -0.07
    лата
    -0.07
     erection
    -0.06
    Located
    -0.06
     보기
    -0.06
    .dump
    -0.06
    .progress
    -0.06
     Surf
    -0.06
    /download
    -0.06
    POSITIVE LOGITS
    мотр
    0.06
    شن
    0.06
    _RD
    0.06
     ولم
    0.06
    most
    0.06
    signature
    0.06
    .Ge
    0.06
    likes
    0.06
    ）は
    0.06
     �
    0.06
    Act Density 0.100%

    No Known Activations