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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ugar
    -0.07
     chocolate
    -0.06
     wonderfully
    -0.06
     Abuse
    -0.06
     heaters
    -0.06
     Highland
    -0.06
    Root
    -0.06
     haze
    -0.06
     bump
    -0.06
     pockets
    -0.06
    POSITIVE LOGITS
     captures
    0.06
    τηγορ
    0.06
     fullWidth
    0.06
    getToken
    0.06
    での
    0.06
    _IDENTIFIER
    0.06
    println
    0.06
     свою
    0.06
    =YES
    0.06
    λω
    0.06
    Act Density 0.134%

    No Known Activations