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

    Neuronpedia

    INDEX
    Explanations

    defining

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igh
    -0.07
     بج
    -0.07
    >T
    -0.06
    ponge
    -0.06
    घ
    -0.06
    aver
    -0.06
    .Local
    -0.06
    _zip
    -0.06
    _PERIOD
    -0.06
     Corpor
    -0.06
    POSITIVE LOGITS
    .delta
    0.06
    例
    0.06
     arranging
    0.06
    .feedback
    0.06
    .multipart
    0.06
    .getUsername
    0.06
    .blog
    0.06
     کسانی
    0.06
     SMALL
    0.06
     greens
    0.06
    Act Density 0.000%

    No Known Activations