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

    Neuronpedia

    INDEX
    Explanations

    key

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mono
    -0.07
    (fmt
    -0.07
    یات
    -0.06
    ुड
    -0.06
    .df
    -0.06
    :@"%@",
    -0.06
     atol
    -0.06
    .ball
    -0.06
     زمانی
    -0.06
     руку
    -0.06
    POSITIVE LOGITS
     основных
    0.07
    ocking
    0.06
     ENTITY
    0.06
    _model
    0.06
    orious
    0.06
    NSObject
    0.06
     chemicals
    0.06
     photoc
    0.06
    obby
    0.06
     rewarding
    0.06
    Act Density 0.000%

    No Known Activations