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

    Neuronpedia

    INDEX
    Explanations

    think

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (pd
    -0.06
     trained
    -0.06
    alous
    -0.06
    _CAMERA
    -0.06
    [ii
    -0.06
    改
    -0.06
     wrestling
    -0.06
    Thrown
    -0.06
     Greg
    -0.06
     //-
    -0.06
    POSITIVE LOGITS
    μενη
    0.07
     APPLE
    0.07
    ！');↵
    0.07
    tps
    0.07
    .Never
    0.06
    NOW
    0.06
    cee
    0.06
     submissions
    0.06
     rebels
    0.06
    的事情
    0.06
    Act Density 0.123%

    No Known Activations