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

    Neuronpedia

    INDEX
    Explanations

    part-time and freelance work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     થય
    0.69
    রণ
    0.67
     क्
    0.66
    泂
    0.66
    干净
    0.65
    ्यूर
    0.64
    န်
    0.63
     सावधान
    0.63
     resaltar
    0.61
    נות
    0.61
    POSITIVE LOGITS
     full
    2.24
     part
    2.04
    full
    1.99
     Full
    1.95
    Full
    1.89
     Part
    1.86
    Part
    1.75
    part
    1.71
     FULL
    1.67
    フル
    1.65
    Act Density 0.164%

    No Known Activations