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

    Neuronpedia

    INDEX
    Explanations

    organizations, institutions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Xt
    -0.07
    了一份
    -0.07
    �
    -0.07
     kg
    -0.06
    .Undef
    -0.06
     lên
    -0.06
    _CHAT
    -0.06
    װ
    -0.06
    幡
    -0.06
    wünsche
    -0.06
    POSITIVE LOGITS
     mog
    0.07
    רוב
    0.07
    _mot
    0.07
    intersect
    0.07
    CreatedBy
    0.07
    blo
    0.07
    .connected
    0.07
    _terminal
    0.07
     Cook
    0.07
    まあ
    0.06
    Act Density 0.250%

    No Known Activations