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

    Neuronpedia

    INDEX
    Explanations

    import Node

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鑣
    0.66
     যাক
    0.62
     கூறியதாவது
    0.59
    군은
    0.58
    ianos
    0.58
     j
    0.57
     term
    0.56
     me
    0.56
    νη
    0.56
     istit
    0.54
    POSITIVE LOGITS
     स्थानांतर
    0.81
     изменения
    0.76
    Trace
    0.74
     Trace
    0.73
     दीर्घ
    0.70
    Tracing
    0.69
     Buren
    0.68
    挼
    0.68
    ⃙
    0.67
    णाम
    0.67
    Act Density 0.000%

    No Known Activations