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

    Neuronpedia

    INDEX
    Explanations

    html code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    es
    1.85
    ו
    1.74
    −−
    1.68
    1.63
    Application
    1.63
     काफ
    1.62
    Архівовано
    1.60
    em
    1.59
    APPLICATION
    1.58
    ನ್ನು
    1.55
    POSITIVE LOGITS
    bleday
    1.84
    𝗳
    1.83
    atele
    1.82
    𝗶
    1.69
    𝘁
    1.65
    𝗮
    1.64
     '-
    1.63
    ',"
    1.61
    𝗿
    1.59
    𝗴
    1.59
    Act Density 0.010%

    No Known Activations