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

    Neuronpedia

    INDEX
    Explanations

    closing braces in code blocks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code-related tokens or bracket-like characters

    np_acts-logits-general · gemini-2.0-flash

    regular expression metacharacters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.61
    Platform
    -0.52
    TagHelpers
    -0.50
    тре
    -0.49
    latform
    -0.48
     Plattform
    -0.48
    果
    -0.48
    //
    -0.47
    yield
    -0.46
    RAINT
    -0.46
    POSITIVE LOGITS
    ConstraintMaker
    0.73
    __":
    0.71
     للاسماء
    0.65
    awtextra
    0.65
    __':
    0.60
    tagHelperRunner
    0.59
    ControllerTest
    0.57
    andReturn
    0.57
    antaranya
    0.56
    runOnUiThread
    0.56
    Act Density 0.016%

    No Known Activations