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

    Neuronpedia

    INDEX
    Explanations

    each one gives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    1.72
    ar
    1.70
    ię
    1.54
     대로
    1.52
    ㅛ
    1.51
    ur
    1.45
     quizás
    1.45
    🆈
    1.45
     करवाने
    1.43
     sonucu
    1.42
    POSITIVE LOGITS
    м
    2.73
    م
    2.34
    म
    2.16
    т
    2.02
    ты
    1.77
    те
    1.59
    та
    1.56
    зе
    1.55
     organelles
    1.55
    ко
    1.54
    Act Density 0.008%

    No Known Activations