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

    Neuronpedia

    INDEX
    Explanations

    free will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     airplane
    -0.09
    Original
    -0.08
     cavern
    -0.08
     bp
    -0.07
     тыся
    -0.07
    OMET
    -0.07
     Georgia
    -0.07
    -th
    -0.07
    ungkin
    -0.07
     other
    -0.07
    POSITIVE LOGITS
    &q
    0.07
    翡
    0.07
    *&
    0.07
    ?option
    0.07
    唐宇
    0.06
    -task
    0.06
    (Role
    0.06
    /*****************************************************************************↵
    0.06
    Xã
    0.06
     contrôle
    0.06
    Act Density 0.024%

    No Known Activations