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

    Neuronpedia

    INDEX
    Explanations

    version numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    อย่าง
    0.64
     양
    0.62
     פר
    0.61
     여
    0.60
     キ
    0.58
     이해
    0.58
     Shyam
    0.57
     오
    0.57
     ト
    0.57
     자동차
    0.57
    POSITIVE LOGITS
    ر
    1.05
    ق
    0.91
    2
    0.88
    1
    0.77
    ר
    0.75
    5
    0.71
    ન
    0.66
    3
    0.64
    ب
    0.64
    4
    0.63
    Act Density 0.059%

    No Known Activations