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

    Neuronpedia

    INDEX
    Explanations

    cries of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    1.29
     are
    1.15
    ’
    1.15
    '
    1.13
    कर
    1.12
    ление
    1.05
    रा
    1.03
    CTION
    1.02
    जन
    1.02
    ys
    1.01
    POSITIVE LOGITS
    تي
    1.02
     prazo
    1.00
    ش
    0.92
     financement
    0.91
    ہ
    0.88
     parler
    0.86
     comprens
    0.85
     ventas
    0.85
    ды
    0.85
    માં
    0.84
    Act Density 0.000%

    No Known Activations