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

    Neuronpedia

    INDEX
    Explanations

    special terms and proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     لأن
    0.76
     saker
    0.71
     ogni
    0.70
     intrinsically
    0.67
     boat
    0.66
     choice
    0.65
     solid
    0.64
     vaste
    0.63
     lucru
    0.63
     sati
    0.63
    POSITIVE LOGITS
    َہ
    0.96
    ဳ
    0.94
    咩
    0.91
     Moments
    0.90
    iony
    0.90
    ΕΣ
    0.87
    ுகிற
    0.85
    衹
    0.84
    ivalence
    0.83
    VIE
    0.82
    Act Density 0.000%

    No Known Activations