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

    Neuronpedia

    INDEX
    Explanations

    sentence structure and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dDays
    0.85
    PopupWindowStyle
    0.84
    ویت
    0.81
     affrontare
    0.81
     کوئی
    0.81
    ColorEffects
    0.80
    ProxyAgent
    0.78
    윰
    0.77
    尃
    0.77
    ێنی
    0.76
    POSITIVE LOGITS
     साथ
    0.76
    $
    0.71
    ouest
    0.70
     един
    0.70
    GED
    0.69
    Bl
    0.68
    iac
    0.67
    RA
    0.67
    est
    0.67
    voice
    0.67
    Act Density 0.000%

    No Known Activations