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

    Neuronpedia

    INDEX
    Explanations

    .Item

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    avax
    -0.07
    hope
    -0.07
    ambiguous
    -0.06
    ler
    -0.06
    슈
    -0.06
    shade
    -0.06
    д
    -0.06
     приз
    -0.06
    ераль
    -0.06
    wicklung
    -0.06
    POSITIVE LOGITS
    기관
    0.07
     �
    0.06
     Tarif
    0.06
    $s
    0.06
     Би
    0.06
    υμ
    0.06
     فريق
    0.06
     Sporting
    0.06
     whereas
    0.06
    ロー
    0.06
    Act Density 0.005%

    No Known Activations