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

    Neuronpedia

    INDEX
    Explanations

    output sections in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diesen
    0.95
    ↵
    0.95
     était
    0.86
         
    0.85
     externe
    0.82
     adulte
    0.82
     interno
    0.80
    0.80
     divertido
    0.79
    ;
    0.78
    POSITIVE LOGITS
    ی
    0.95
    time
    0.88
    dynamic
    0.83
    number
    0.80
    ا
    0.78
    disturbance
    0.78
    ல்
    0.77
    น
    0.77
    Α
    0.76
    いた
    0.74
    Act Density 0.000%

    No Known Activations