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

    Neuronpedia

    INDEX
    Explanations

    background

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    women
    -0.07
     women
    -0.07
     clerk
    -0.07
    clinical
    -0.06
    ('--
    -0.06
     сіль
    -0.06
    县
    -0.06
    动生成
    -0.06
     країни
    -0.06
     FreeBSD
    -0.06
    POSITIVE LOGITS
     Magnum
    0.06
    âr
    0.06
    ное
    0.06
    TN
    0.06
    ew
    0.06
    '>
↵
    0.06
     histo
    0.06
    ัช
    0.06
     зас
    0.06
    _bases
    0.06
    Act Density 0.005%

    No Known Activations