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

    Neuronpedia

    INDEX
    Explanations

    list items and colons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ક્તિ
    0.62
     construcción
    0.54
     pierde
    0.50
    ји
    0.50
    zyła
    0.49
     fün
    0.48
     Nunca
    0.48
     cinci
    0.47
     সন্ত্রাসী
    0.47
    fromRGB
    0.46
    POSITIVE LOGITS
    Table
    0.53
    :
    0.49
     patterns
    0.44
    Elastic
    0.43
    Sil
    0.42
     Cases
    0.42
    Decor
    0.42
    弥
    0.41
    apd
    0.41
    Pharmac
    0.41
    Act Density 0.002%

    No Known Activations