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

    Neuronpedia

    INDEX
    Explanations

    whole number amounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ֿ
    0.96
    وا
    0.87
    ecause
    0.81
    با
    0.80
    گوید
    0.80
    andosi
    0.77
     সঙ্গে
    0.77
     śmier
    0.77
     видели
    0.77
     সীমান্তের
    0.76
    POSITIVE LOGITS
    лены
    0.72
    HER
    0.70
     পাঁচ
    0.69
    MES
    0.69
     queens
    0.68
     Chas
    0.68
     Gesam
    0.68
    рый
    0.67
     पाँच
    0.67
    czną
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.