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

    Neuronpedia

    INDEX
    Explanations

    code generation constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    toISOString
    0.37
    ኒ
    0.37
    ʎ
    0.36
    של
    0.35
    len
    0.35
     lenght
    0.34
    ต้
    0.34
    тное
    0.34
    interpr
    0.34
     첨
    0.34
    POSITIVE LOGITS
     sprayer
    0.42
     Chas
    0.40
     ইউনিক
    0.40
     Conner
    0.39
     Jamie
    0.39
     Sv
    0.38
     Cosmetic
    0.38
    nBitCount
    0.38
     robotics
    0.38
     Early
    0.38
    Act Density 0.000%

    No Known Activations