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

    Neuronpedia

    INDEX
    Explanations

    Republican Abraham

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    1.09
     komple
    0.99
    Nicht
    0.98
    ﻡ
    0.97
    يل
    0.94
     quelconque
    0.94
     (!
    0.92
    ل
    0.91
     sağlan
    0.90
     رف
    0.90
    POSITIVE LOGITS
    闱
    1.03
    声
    1.03
    玺
    0.98
     garner
    0.97
    তন্ত্র
    0.94
    合
    0.93
    EMY
    0.92
     antiques
    0.91
    nex
    0.90
    魅
    0.90
    Act Density 0.000%

    No Known Activations