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

    Neuronpedia

    INDEX
    Explanations

    crimes and their types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     спустя
    0.86
     +=
    0.85
    <0x80>
    0.83
    ially
    0.82
    ic
    0.78
     点击
    0.77
    },
    0.74
     /$
    0.73
    ulous
    0.73
    iales
    0.71
    POSITIVE LOGITS
    ເຄື່ອງ
    0.99
    ເປັນ
    0.91
     Coachella
    0.89
    الی
    0.88
     рекомендации
    0.88
    আন
    0.86
    ुली
    0.84
    ເຈ
    0.84
    吉
    0.84
     Tendulkar
    0.83
    Act Density 0.000%

    No Known Activations