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

    Neuronpedia

    INDEX
    Explanations

    units of measurement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ท
    0.60
    та
    0.55
    да
    0.51
    ری
    0.50
     çalışt
    0.50
    ња
    0.50
    на
    0.49
    ³
    0.49
    лы
    0.49
    ure
    0.49
    POSITIVE LOGITS
     momentous
    0.59
    ？
    0.57
     monopolist
    0.55
    rž
    0.54
     keyed
    0.53
     championed
    0.52
    ‌است
    0.52
    రుగు
    0.52
    pecific
    0.51
     antico
    0.50
    Act Density 0.020%

    No Known Activations