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

    Neuronpedia

    INDEX
    Explanations

    code elements and structures related to programming or software development

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

    Tokens followed by "composed" or "component"

    np_acts-logits-general · gemini-2.0-flash

    composed of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Meksiku
    -0.65
    AndEndTag
    -0.62
    findpost
    -0.62
     useStyles
    -0.59
     altars
    -0.58
     altar
    -0.56
    ieteur
    -0.56
    ngdoc
    -0.55
     Egli
    -0.55
     Aza
    -0.55
    POSITIVE LOGITS
     comp
    2.30
     Comp
    2.26
     Com
    2.24
     COM
    2.22
    Comp
    2.19
    comp
    2.19
    COM
    2.12
    Com
    2.12
     kom
    2.11
     Kom
    2.07
    Act Density 0.256%

    No Known Activations