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

    Neuronpedia

    INDEX
    Explanations

    drinking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (layout
    -0.07
     cerebral
    -0.07
    董事
    -0.06
    纮
    -0.06
    赈
    -0.06
     jumped
    -0.06
    amer
    -0.06
     cdr
    -0.06
    赢家
    -0.06
    財
    -0.06
    POSITIVE LOGITS
    所需要的
    0.08
    idl
    0.07
     çalışm
    0.07
     TL
    0.07
     rested
    0.07
    license
    0.07
     dan
    0.07
    DCF
    0.07
    <L
    0.07
    İLİ
    0.07
    Act Density 0.006%

    No Known Activations