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

    Neuronpedia

    INDEX
    Explanations

    Agreements and decisions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tissue
    -0.07
    &r
    -0.07
     лют
    -0.06
     sabot
    -0.06
    我的
    -0.06
    STALL
    -0.06
     HOLDER
    -0.06
    acimiento
    -0.06
     Waist
    -0.06
     شكل
    -0.06
    POSITIVE LOGITS
    <<"
    0.07
    .shop
    0.06
    .current
    0.06
     آزمون
    0.06
    FullScreen
    0.06
     �
    0.06
     mal
    0.06
    �
    0.06
    +='<
    0.06
     еп
    0.06
    Act Density 0.075%

    No Known Activations