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

    Neuronpedia

    INDEX
    Explanations

    PIN Code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ěla
    0.80
     campeonato
    0.79
    cej
    0.76
    obat
    0.73
    ına
    0.72
    itorios
    0.72
    くちゃ
    0.71
     اقتصاد
    0.71
     abiert
    0.70
    eba
    0.70
    POSITIVE LOGITS
    t
    1.26
    ف
    1.12
    耆
    1.02
    ش
    0.95
    ください
    0.94
    т
    0.94
    ع
    0.93
    倘
    0.92
    ्ड
    0.90
    ます
    0.90
    Act Density 0.000%

    No Known Activations