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

    Neuronpedia

    INDEX
    Explanations

    degrees of separation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    094
    -0.07
    Equals
    -0.07
     kurulan
    -0.06
    /random
    -0.06
     вместе
    -0.06
    当
    -0.06
     performers
    -0.06
     jurisdictions
    -0.06
     flashing
    -0.06
    бо
    -0.06
    POSITIVE LOGITS
    (Image
    0.08
    lish
    0.07
     ”↵
    0.07
     Mods
    0.07
     agr
    0.06
     ):↵
    0.06
    input
    0.06
     Total
    0.06
    рук
    0.06
     bizarre
    0.06
    Act Density 0.000%

    No Known Activations