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

    Neuronpedia

    INDEX
    Explanations

    different

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AL
    0.85
    н
    0.77
    il
    0.70
    ن
    0.67
    ン
    0.67
     stesso
    0.66
     Dopo
    0.66
     MyDB
    0.64
    EN
    0.63
    ని
    0.63
    POSITIVE LOGITS
     emph
    0.78
    iation
    0.72
    eur
    0.68
    féle
    0.68
    ла
    0.67
    वालों
    0.66
     взгля
    0.66
     మాట
    0.66
    பட்ட
    0.65
     مواقع
    0.65
    Act Density 0.030%

    No Known Activations