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

    Neuronpedia

    INDEX
    Explanations

    major technology companies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ü
    1.23
    А
    1.23
    ாய
    1.19
     cyberspace
    1.15
    AY
    1.14
    <0xB2>
    1.11
    보면
    1.09
    Н
    1.09
     afar
    1.08
     Еще
    1.08
    POSITIVE LOGITS
    s
    1.20
    isering
    1.08
    스러운
    1.08
    is
    1.07
     relleno
    1.07
     berakhir
    1.05
    ir
    0.98
     아닌
    0.98
    ج
    0.98
    idade
    0.97
    Act Density 0.097%

    No Known Activations