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

    Neuronpedia

    INDEX
    Explanations

    lacking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     countdown
    -0.07
    automation
    -0.07
     MTV
    -0.06
    razione
    -0.06
     cared
    -0.06
     Internet
    -0.06
    .activities
    -0.06
     Natal
    -0.06
     anche
    -0.06
     Sat
    -0.06
    POSITIVE LOGITS
     tbsp
    0.07
     gems
    0.07
    -sided
    0.07
     품
    0.07
    аток
    0.07
     zie
    0.06
     ка
    0.06
     missing
    0.06
     jit
    0.06
    ظام
    0.06
    Act Density 0.005%

    No Known Activations