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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    價
    -0.08
    Variant
    -0.08
     pregnant
    -0.08
     lekker
    -0.07
    ippi
    -0.07
    ustom
    -0.07
     الليبي
    -0.07
     medic
    -0.07
    etically
    -0.07
    גרמניה
    -0.07
    POSITIVE LOGITS
    就成了
    0.08
    _algorithm
    0.08
    ᵎ
    0.08
     DAO
    0.07
     pouring
    0.07
    沙龙
    0.07
     AUTH
    0.07
    海口
    0.07
     Vault
    0.07
     האחרון
    0.07
    Act Density 0.010%

    No Known Activations