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

    Neuronpedia

    INDEX
    Explanations

    electron microscopy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     displ
    0.64
     permite
    0.62
     فصل
    0.58
     ох
    0.57
    i
    0.55
    d
    0.55
     сообщи
    0.54
     beho
    0.54
     decir
    0.53
    ^
    0.53
    POSITIVE LOGITS
    之间的
    0.58
    ان
    0.52
    之间
    0.50
    概率
    0.50
    ার
    0.50
    之外
    0.50
    自
    0.50
    IER
    0.49
     tussen
    0.48
    ész
    0.48
    Act Density 0.000%

    No Known Activations