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

    Neuronpedia

    INDEX
    Explanations

    Statistics or job postings. I will pick the shorter answer: Statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .respond
    -0.07
    نموذ
    -0.07
    幸运
    -0.06
    我记得
    -0.06
     thuốc
    -0.06
    疰
    -0.06
    傕
    -0.06
     recursion
    -0.06
    市县
    -0.06
    סין
    -0.06
    POSITIVE LOGITS
     gent
    0.08
    -fashioned
    0.07
    ]}"
    0.07
    expression
    0.06
    Mex
    0.06
    所示
    0.06
    _encoded
    0.06
     dialogs
    0.06
     composed
    0.06
     Hawth
    0.06
    Act Density 0.043%

    No Known Activations