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

    Neuronpedia

    INDEX
    Explanations

    programming lookup by identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ።
    0.78
     ちゃう
    0.77
     الكسور
    0.76
     ပြော
    0.71
     تړل
    0.71
    formen
    0.70
     พิจิก
    0.70
     horrific
    0.70
     ながら
    0.70
    јединачна
    0.69
    POSITIVE LOGITS
    م
    0.93
    ا
    0.89
    na
    0.86
    i
    0.84
    ,
    0.84
    ni
    0.83
    u
    0.83
    श
    0.83
    so
    0.79
    ని
    0.79
    Act Density 0.000%

    No Known Activations