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

    Neuronpedia

    INDEX
    Explanations

    image data or URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pavattati
    0.47
    ثله
    0.43
     pavatt
    0.42
     каттоосуз
    0.42
    耠
    0.42
     యూ
    0.41
     लाइब्रेरी
    0.41
    プリング
    0.41
    tDBOutput
    0.40
     granularity
    0.40
    POSITIVE LOGITS
    0.52
    br
    0.44
     te
    0.42
    that
    0.41
    edo
    0.40
    ♦
    0.40
    aven
    0.40
     Months
    0.40
    street
    0.39
    expressions
    0.39
    Act Density 0.003%

    No Known Activations