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

    Neuronpedia

    INDEX
    Explanations

    text expansion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ماً
    0.64
    ↵
    0.62
    宪
    0.58
     му
    0.57
     محدود
    0.55
    addAlignment
    0.55
     mocy
    0.55
    機会
    0.55
     ну
    0.54
    établ
    0.54
    POSITIVE LOGITS
    ULATIONS
    0.91
    Nano
    0.88
    List
    0.87
    Ě
    0.87
    Nan
    0.85
    EditText
    0.84
    É
    0.84
    LL
    0.84
    િંગ
    0.84
     nanofibers
    0.83
    Act Density 0.004%

    No Known Activations