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

    Neuronpedia

    INDEX
    Explanations

    Code/Technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tidy
    -0.06
    safe
    -0.06
    }")
    -0.06
     clocks
    -0.06
     lá
    -0.06
     poměr
    -0.06
    ぅ
    -0.06
    _study
    -0.06
     ΕΛ
    -0.06
    (SYS
    -0.06
    POSITIVE LOGITS
    メント
    0.07
    reated
    0.06
    (Op
    0.06
     ambient
    0.06
     دکتر
    0.06
     При
    0.06
    했다
    0.06
     Autor
    0.06
    [mask
    0.06
    'av
    0.06
    Act Density 0.000%

    No Known Activations