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

    Neuronpedia

    INDEX
    Explanations

    Explanatory text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "][
    -0.06
    Trad
    -0.06
    }`);↵↵
    -0.06
    -db
    -0.06
    abouts
    -0.06
     embr
    -0.06
     OTP
    -0.06
    ันน
    -0.06
    .INTEGER
    -0.06
     australia
    -0.06
    POSITIVE LOGITS
     also
    0.08
     intercept
    0.07
    YO
    0.07
     companion
    0.06
    .io
    0.06
     Eisen
    0.06
     met
    0.06
     IA
    0.06
     skeletons
    0.06
    _GRAY
    0.06
    Act Density 0.013%

    No Known Activations