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

    Neuronpedia

    INDEX
    Explanations

    physical places

    np_acts-logits-general · gemini-2.5-flash-lite

    chaincode or line code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تي
    0.90
    st
    0.88
    t
    0.88
    (
    0.82
    ש
    0.80
    تها
    0.79
    dh
    0.79
    রা
    0.77
    יו
    0.77
    ר
    0.77
    POSITIVE LOGITS
     อาจ
    0.73
    아야
    0.71
     corridors
    0.70
     grasses
    0.70
     pask
    0.70
    ॉफ्ट
    0.70
     asuntos
    0.70
    ある
    0.69
    𝗖
    0.69
     سر
    0.69
    Act Density 1.370%

    No Known Activations