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

    Neuronpedia

    INDEX
    Explanations

    confusing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    っ
    0.77
    πισ
    0.74
    ने
    0.73
    ăt
    0.73
    optimal
    0.73
    ér
    0.72
    cio
    0.72
    ייתה
    0.71
    ً
    0.70
    rule
    0.70
    POSITIVE LOGITS
     varies
    1.06
     ebenfalls
    1.04
     varie
    0.95
     ebenso
    0.94
     includes
    0.87
     също
    0.87
    同樣
    0.87
     relacionamento
    0.85
     بسیار
    0.85
     zeer
    0.85
    Act Density 1.118%

    No Known Activations