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

    Neuronpedia

    INDEX
    Explanations

    Google Assistant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    entery
    0.82
     quizá
    0.80
    aroos
    0.78
     시절
    0.76
    lineWidth
    0.76
     ഉത്സ
    0.75
    కరణ
    0.75
     사건
    0.75
     či
    0.74
     suasana
    0.74
    POSITIVE LOGITS
    на
    0.85
    憎
    0.75
    лох
    0.75
     ECONOMIC
    0.71
    न
    0.69
    GPUs
    0.68
    ان
    0.68
     igneous
    0.68
     profinite
    0.68
    ל
    0.66
    Act Density 0.002%

    No Known Activations