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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal and decimal numbers, often within code-like contexts or formatted strings

    oai_token-act-pair · gemini-2.0-flash

    code and technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '}),
    -0.52
    "])
    -0.51
    ".
    -0.48
    annica
    -0.48
    "){
    -0.47
    Beijos
    -0.46
    "]);
    -0.45
    '));
    -0.45
    AndEndTag
    -0.44
    migrationBuilder
    -0.44
    POSITIVE LOGITS
    CloseOperation
    0.72
     betweenstory
    0.71
    حياته
    0.60
     Ceramby
    0.60
     Sociale
    0.58
    RegressionTest
    0.57
     Stray
    0.55
     zoude
    0.54
     Stub
    0.53
    Lone
    0.53
    Act Density 0.873%

    No Known Activations