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

    Neuronpedia

    INDEX
    Explanations

    assembly code and its instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    坭
    1.01
     sábado
    0.88
    Ꮙ
    0.82
    inama
    0.80
    derdag
    0.80
     trailed
    0.80
    種類の
    0.80
     tyranny
    0.80
    𝖎
    0.78
    當
    0.78
    POSITIVE LOGITS
    гал
    0.76
                
    0.75
    ണ്ണി
    0.74
    Muhammad
    0.73
    ễ
    0.73
     Ill
    0.72
     हरियाणा
    0.72
    رہ
    0.71
     Dewan
    0.71
    ทาง
    0.70
    Act Density 0.076%

    No Known Activations