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

    Neuronpedia

    INDEX
    Explanations

    factor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PROD
    -0.08
    лод
    -0.07
    _logout
    -0.07
    .currentPage
    -0.07
    '";
↵
    -0.06
    larına
    -0.06
     courage
    -0.06
    noon
    -0.06
    入れ
    -0.06
     исследования
    -0.06
    POSITIVE LOGITS
     Angeles
    0.07
    Connell
    0.07
     นาง
    0.07
    807
    0.06
    ewire
    0.06
    목
    0.06
    ="--
    0.06
    Defs
    0.06
    wine
    0.06
    فة
    0.06
    Act Density 0.000%

    No Known Activations