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

    Neuronpedia

    INDEX
    Explanations

    script run directly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     shoal
    0.41
     propon
    0.39
    訲
    0.38
     availability
    0.38
     প্রাপ্য
    0.38
     beschikbaar
    0.37
     dostępne
    0.37
    有了
    0.36
     पुराने
    0.36
    可以使用
    0.36
    POSITIVE LOGITS
     directly
    0.74
    直接
    0.72
     직접
    0.69
     напрямую
    0.67
     直接
    0.64
    directly
    0.63
     Directly
    0.62
     directe
    0.60
     directement
    0.60
     direkt
    0.59
    Act Density 0.003%

    No Known Activations