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

    Neuronpedia

    INDEX
    Explanations

    "at its core"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    USTER
    -0.07
    etty
    -0.07
     (-
    -0.07
    _nn
    -0.06
    },
↵
↵
    -0.06
    決定
    -0.06
     Regardless
    -0.06
    ۰
    -0.06
     dece
    -0.06
     █████
    -0.06
    POSITIVE LOGITS
     textarea
    0.07
    บน
    0.06
    imetype
    0.06
     markup
    0.06
     Objects
    0.06
    후
    0.06
     зараз
    0.06
    vat
    0.06
    .warning
    0.06
    arn
    0.06
    Act Density 0.206%

    No Known Activations