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

    Neuronpedia

    INDEX
    Explanations

    negative charge or consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ków
    2.33
    purse
    2.19
    lardan
    2.05
    लिये
    2.02
    væ
    1.96
    v
    1.95
    sa
    1.92
    ни
    1.91
    jumlah
    1.90
    τες
    1.87
    POSITIVE LOGITS
    ت
    2.67
    학과
    1.90
    خ
    1.77
     बढ़ते
    1.76
    ing
    1.75
    تف
    1.75
    没有
    1.73
    تس
    1.72
    تمر
    1.67
     afar
    1.66
    Act Density 0.784%

    No Known Activations