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

    Neuronpedia

    INDEX
    Explanations

    formulaic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    á
    1.59
    ד
    1.48
    w
    1.41
    ப
    1.40
    一
    1.38
    د
    1.35
    é
    1.34
    צ
    1.27
    手
    1.25
    ي
    1.23
    POSITIVE LOGITS
    м
    1.52
    ம்
    1.12
    toare
    1.11
     by
    0.96
    ни
    0.87
     washington
    0.86
    joner
    0.84
    sning
    0.83
    یی
    0.82
    нг
    0.81
    Act Density 0.000%

    No Known Activations