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

    Neuronpedia

    INDEX
    Explanations

    lang and encoding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Пр
    -0.07
    @d
    -0.07
     butto
    -0.07
    Пол
    -0.07
     filthy
    -0.06
    essage
    -0.06
    edTextBox
    -0.06
    Clin
    -0.06
     Amsterdam
    -0.06
    _texts
    -0.06
    POSITIVE LOGITS
    ')");↵
    0.06
    ).'</
    0.06
     persuade
    0.06
     çeşitli
    0.06
     ),
↵
    0.06
    CString
    0.06
     argued
    0.06
    ppers
    0.06
     arguing
    0.06
    事情
    0.06
    Act Density 0.001%

    No Known Activations