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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Comparative
    -0.07
     Ip
    -0.06
     elif
    -0.06
    js
    -0.06
    たく
    -0.06
    _Play
    -0.06
    .go
    -0.06
    _bonus
    -0.06
    human
    -0.06
     Nacht
    -0.06
    POSITIVE LOGITS
    /Sh
    0.07
    该
    0.07
     제가
    0.07
     extingu
    0.07
     خوان
    0.07
    การจ
    0.07
    °
    0.06
    �
    0.06
     клуб
    0.06
     �
    0.06
    Act Density 0.052%

    No Known Activations