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

    Neuronpedia

    INDEX
    Explanations

    socks, toys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    НЫ
    1.91
     веществ
    1.68
     CGPoint
    1.59
    ្នុង
    1.58
    dbjc
    1.57
     hukum
    1.57
     зрения
    1.56
     conclusively
    1.55
    দের
    1.54
    ascimento
    1.52
    POSITIVE LOGITS
    tid
    2.10
    tod
    1.92
    tio
    1.90
    te
    1.89
    ت
    1.86
    𝑡
    1.84
    tin
    1.83
    पात
    1.83
    tie
    1.82
    tree
    1.81
    Act Density 0.058%

    No Known Activations