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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    öt
    -0.08
    opc
    -0.07
     nett
    -0.07
    napshot
    -0.07
    nung
    -0.07
     ад
    -0.07
     hObject
    -0.07
    ólogo
    -0.07
    鳥
    -0.07
    吉林
    -0.06
    POSITIVE LOGITS
    _weapon
    0.09
     Example
    0.07
     revealing
    0.07
     Dating
    0.07
    createCommand
    0.07
     تصني
    0.07
    _tbl
    0.07
     ...\
    0.07
     Bal
    0.07
    CISION
    0.07
    Act Density 0.001%

    No Known Activations