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

    Neuronpedia

    INDEX
    Explanations

    according

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prostitut
    -0.09
    idential
    -0.08
    Barcode
    -0.07
    creative
    -0.07
    _DISCONNECT
    -0.07
     extern
    -0.07
    .TEXTURE
    -0.07
     Reign
    -0.07
    _extension
    -0.06
     وجه
    -0.06
    POSITIVE LOGITS
    istrar
    0.07
     screenings
    0.07
    最大化
    0.07
    🧐
    0.07
    多久
    0.07
    维
    0.06
    产业基地
    0.06
    嘉年华
    0.06
    oger
    0.06
    owania
    0.06
    Act Density 0.004%

    No Known Activations