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

    Neuronpedia

    INDEX
    Explanations

    capitalized terms in code

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.64
    */;
    -0.60
    reszcie
    -0.54
     AssemblyCulture
    -0.50
     ModelExpression
    -0.49
    ViewChild
    -0.48
     saites
    -0.47
     Fundament
    -0.47
    throwing
    -0.46
     الدولى
    -0.45
    POSITIVE LOGITS
    <bos>
    0.92
    rungsseite
    0.63
     NgModule
    0.59
    NewReader
    0.59
    はじめに
    0.59
    +#+
    0.58
    Rüyada
    0.53
    …~
    0.50
    utnik
    0.50
     Jow
    0.50
    Act Density 55.783%

    No Known Activations