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

    Neuronpedia

    INDEX
    Explanations

    Kent and Dover locations, Fujian province

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.74
     execute
    0.70
    ে
    0.68
    न
    0.68
     interrupt
    0.67
     adhere
    0.66
     expiresIn
    0.66
     anointed
    0.65
     אמ
    0.63
     marqués
    0.63
    POSITIVE LOGITS
    ow
    0.72
    ва
    0.72
    ]
    0.70
    ially
    0.69
    VX
    0.66
     ہوا۔
    0.65
     ذریع
    0.64
    豆
    0.64
    ه‌ی
    0.62
    題
    0.62
    Act Density 0.001%

    No Known Activations