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

    Neuronpedia

    INDEX
    Explanations

    fragments of code with structural programming syntax, like parentheses and brackets

    oai_token-act-pair · gemini-2.0-flash

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     asupra
    -0.59
     estimés
    -0.56
    /******/
    -0.52
     hoogte
    -0.51
     sống
    -0.48
    勝手に
    -0.48
    érience
    -0.48
     rápidas
    -0.47
     cerdas
    -0.46
    */),
    -0.46
    POSITIVE LOGITS
    contentLoaded
    0.83
    WithIOException
    0.71
    хьтан
    0.70
     ligiloj
    0.65
    parsedMessage
    0.65
     برانيه
    0.62
     rerum
    0.59
    ANTLR
    0.59
    addCriterion
    0.59
    protoc
    0.58
    Act Density 3.932%

    No Known Activations