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

    Neuronpedia

    INDEX
    Explanations

    code snippets using semi-colons, numbers, and square brackets to denote either code or citations

    oai_token-act-pair · gemini-2.0-flash

    Code/references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DllImport
    -0.63
    )',
    -0.53
    XmlRootElement
    -0.52
    )",
    -0.48
    }',
    -0.48
     Poni
    -0.48
     Constitu
    -0.47
    }`,
    -0.46
    '};
    -0.46
    ...",
    -0.45
    POSITIVE LOGITS
     للمعارف
    0.98
    ThroughAttribute
    0.70
    Kjelder
    0.65
    ၊
    0.65
    setContentView
    0.64
    HasForeignKey
    0.62
    FieldNumber
    0.61
     "..\..\
    0.60
     AssemblyCulture
    0.58
    esterno
    0.57
    Act Density 4.580%

    No Known Activations