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

    Neuronpedia

    INDEX
    Explanations

    numbers and durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.74
    ar
    0.66
    a
    0.64
    ات
    0.63
    or
    0.62
    oretically
    0.62
    х
    0.61
    다른
    0.61
    ের
    0.61
    er
    0.61
    POSITIVE LOGITS
    ANGE
    0.59
     Antennes
    0.57
    omanian
    0.57
     Premises
    0.56
    ͹
    0.56
    ুই
    0.55
    स्कृतिक
    0.55
     imprisonment
    0.54
    ဦ
    0.54
    uintes
    0.54
    Act Density 0.315%

    No Known Activations