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

    Neuronpedia

    INDEX
    Explanations

    pre-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     चाह
    1.06
    焦點
    1.05
    まま
    1.03
     FormsModule
    1.03
    ів
    1.01
     मेहन
    1.01
    emb
    0.99
    贸
    0.98
     философия
    0.97
    把
    0.97
    POSITIVE LOGITS
    в
    1.05
     từng
    0.96
     گوئیاں
    0.95
    ag
    0.91
    ফুল্ল
    0.89
    CIS
    0.89
    card
    0.88
    우스
    0.86
    াহ
    0.86
    ve
    0.85
    Act Density 0.044%

    No Known Activations