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

    Neuronpedia

    INDEX
    Explanations

    connecting words/punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $IFn
    -0.07
     campaigned
    -0.06
    )row
    -0.06
    )::
    -0.06
    -photo
    -0.06
     okul
    -0.06
    ск
    -0.06
     norsk
    -0.05
    experimental
    -0.05
    σιμο
    -0.05
    POSITIVE LOGITS
    .titleLabel
    0.07
     Charleston
    0.07
     taxpayer
    0.07
    oned
    0.07
     apa
    0.07
    _prov
    0.07
    itate
    0.06
    supported
    0.06
    atte
    0.06
    чик
    0.06
    Act Density 0.018%

    No Known Activations