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

    Neuronpedia

    INDEX
    Explanations

    during a time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     duration
    0.94
     durata
    0.82
     vomiting
    0.79
     longest
    0.79
    adecimal
    0.74
    noon
    0.72
    longest
    0.71
    minded
    0.71
     पर्यंत
    0.71
    จบ
    0.71
    POSITIVE LOGITS
    لما
    0.96
    ل
    0.89
    й
    0.85
    au
    0.83
    ル
    0.80
    ak
    0.79
    k
    0.79
     прави
    0.79
    ช่วยเหลือ
    0.77
    z
    0.76
    Act Density 0.053%

    No Known Activations