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

    Neuronpedia

    INDEX
    Explanations

    Arch Linux

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وعلى
    1.34
    ز
    1.15
    bam
    1.01
    skraft
    1.01
    بن
    0.99
    ی
    0.99
    شو
    0.98
    และความ
    0.95
    נים
    0.95
    ка
    0.94
    POSITIVE LOGITS
    الإ
    1.16
    ০০
    1.11
    ТЕ
    1.06
     finalidad
    1.05
     notizie
    1.05
     infine
    1.04
    TE
    1.02
     piedi
    1.00
     intercambio
    0.99
     rimane
    0.99
    Act Density 0.052%

    No Known Activations