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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    His
    -0.08
    Power
    -0.08
    Many
    -0.07
     stroke
    -0.07
    enums
    -0.07
     LDL
    -0.06
    The
    -0.06
    David
    -0.06
     exhibitions
    -0.06
    919
    -0.06
    POSITIVE LOGITS
    ่สามารถ
    0.07
     ≠
    0.07
    :none
    0.06
    可是
    0.06
    _InitStruct
    0.06
     Получ
    0.06
     �
    0.06
    firm
    0.06
    .rest
    0.06
     trouvé
    0.06
    Act Density 0.044%

    No Known Activations