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

    Neuronpedia

    INDEX
    Explanations

    success

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oglycos
    2.11
    ுள்ளார்
    2.08
    서는
    2.05
    scopic
    2.00
    sticks
    1.95
     съм
    1.92
    rates
    1.83
     sensibilities
    1.82
    時候
    1.75
    ことを
    1.72
    POSITIVE LOGITS
    াত
    1.99
    ému
    1.93
    йи
    1.84
    ist
    1.83
    ண
    1.82
    ier
    1.80
    ै
    1.76
    膑
    1.73
    ون
    1.73
    ین
    1.69
    Act Density 0.034%

    No Known Activations