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

    Neuronpedia

    INDEX
    Explanations

    Last followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     கட்டுமானம்
    0.81
     steady
    0.79
     ቀላል
    0.75
    PIO
    0.75
     мере
    0.73
     மோச
    0.73
    Celeron
    0.73
     alfabet
    0.73
    和一个
    0.73
     renseign
    0.72
    POSITIVE LOGITS
     minute
    0.78
    рию
    0.72
    minute
    0.72
     McCall
    0.72
    emorrh
    0.71
     Resort
    0.69
    handled
    0.68
    CIÓN
    0.67
     Minute
    0.67
    বাঁ
    0.65
    Act Density 0.076%

    No Known Activations