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

    Neuronpedia

    INDEX
    Explanations

    formatting language, code, and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Birds
    1.04
     Keep
    1.00
     descarg
    0.98
     Behold
    0.98
     पढ़े
    0.97
     используется
    0.95
     зовут
    0.94
    這是
    0.94
     Spacious
    0.94
     Nam
    0.93
    POSITIVE LOGITS
     $^{\
    1.10
    {\'
    1.06
    \&
    0.97
    ${
    0.91
    ''
    0.91
    [\
    0.89
    \/}
    0.87
    }&
    0.86
    "/
    0.85
    locations
    0.85
    Act Density 0.142%

    No Known Activations