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

    Neuronpedia

    INDEX
    Explanations

    structured comment syntax and formatting elements in code

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

    legal definitions or programming snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tuot
    -0.33
    .*")]
    -0.33
     falschen
    -0.32
    pantalón
    -0.31
     ejército
    -0.31
     boneka
    -0.31
     păr
    -0.31
     jembatan
    -0.30
    esercito
    -0.30
     verschiedene
    -0.30
    POSITIVE LOGITS
    tagext
    0.68
     للمعارف
    0.67
    WriteTagHelper
    0.65
     esternos
    0.63
    出版年
    0.61
     '\\;'
    0.59
     Италијани
    0.59
    MigrationBuilder
    0.59
    tagHelperRunner
    0.58
    verifyException
    0.58
    Act Density 0.070%

    No Known Activations