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

    Neuronpedia

    INDEX
    Explanations

    prefixes of specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     URANIUM
    0.85
    ixas
    0.84
     stockbild
    0.84
     வெளியிட
    0.81
    usetzen
    0.81
     purported
    0.79
    煐
    0.79
    ইসলাম
    0.79
    contrad
    0.79
    끙
    0.78
    POSITIVE LOGITS
     Tous
    0.72
    Thời
    0.67
    P
    0.64
     וא
    0.64
    חיל
    0.64
    ｜
    0.63
    Plus
    0.62
     Thời
    0.62
     Dest
    0.62
     Projects
    0.62
    Act Density 0.399%

    No Known Activations