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

    Neuronpedia

    INDEX
    Explanations

    brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    痰
    -0.08
     nữ
    -0.08
    难受
    -0.08
     Tek
    -0.07
    することで
    -0.07
     spontaneous
    -0.07
    בית
    -0.07
    出门
    -0.07
     remed
    -0.07
     Jensen
    -0.07
    POSITIVE LOGITS
    -ID
    0.07
    agency
    0.07
    -eslint
    0.07
    (cart
    0.06
    format
    0.06
    ั
    0.06
    ?'
    0.06
    �
    0.06
    フィ
    0.06
    take
    0.06
    Act Density 0.002%

    No Known Activations