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

    Neuronpedia

    INDEX
    Explanations

    technical language related to computing configurations and commands

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

    XML attributes, code initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.70
     wikipagina
    -0.66
     चीज़ों
    -0.62
    tagHelperRunner
    -0.60
     turg
    -0.56
    niſſe
    -0.55
    iſchen
    -0.54
    〮
    -0.54
     diſt
    -0.54
     surla
    -0.54
    POSITIVE LOGITS
     defaultstate
    0.39
    VersionUID
    0.39
    autoreleasepool
    0.37
     Roskov
    0.37
    GenerationType
    0.33
    rawtypes
    0.33
    ApiModelProperty
    0.33
    Personendaten
    0.32
    TagHelpers
    0.31
    Nationalité
    0.30
    Act Density 0.093%

    No Known Activations