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

    Neuronpedia

    INDEX
    Explanations

    to ensure or to research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺭ
    0.88
    ikten
    0.84
    beginning
    0.82
     kejadian
    0.80
     gdy
    0.79
     resul
    0.78
    们
    0.78
    resu
    0.77
    ரமாக
    0.77
    patent
    0.75
    POSITIVE LOGITS
    ن
    0.81
    те
    0.79
    >∕
    0.79
    ്
    0.76
    ब
    0.75
    न
    0.74
    Ճ
    0.73
    െ
    0.71
    ्ला
    0.69
    ્સ
    0.69
    Act Density 0.000%

    No Known Activations