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

    Neuronpedia

    INDEX
    Explanations

    public incidents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    坐在
    -0.07
     apprent
    -0.06
    一切
    -0.06
    анси
    -0.06
    adients
    -0.06
    (animation
    -0.06
    ;l
    -0.06
    .fail
    -0.06
    нути
    -0.06
    orque
    -0.06
    POSITIVE LOGITS
    Management
    0.07
     hơi
    0.07
    _minutes
    0.07
    |[
    0.06
     emb
    0.06
     Trusted
    0.06
     etmiştir
    0.06
    ?
    0.06
    รอง
    0.06
    $s
    0.06
    Act Density 0.002%

    No Known Activations