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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vu
    -0.08
    ’hui
    -0.07
     kleinen
    -0.07
    ***/↵
    -0.07
    olley
    -0.07
     Homes
    -0.07
    Vu
    -0.06
    _ENABLED
    -0.06
    Whole
    -0.06
    ARING
    -0.06
    POSITIVE LOGITS
     as
    0.08
    .GetName
    0.07
     Bras
    0.07
    .setdefault
    0.07
    西
    0.07
     getPassword
    0.06
    ,pos
    0.06
    SAM
    0.06
     escap
    0.06
    .as
    0.06
    Act Density 0.014%

    No Known Activations