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

    Neuronpedia

    INDEX
    Explanations

    the presence of a block or marker indicating the start of a new segment or section

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

    Tokens followed by punctuation or numbers

    np_acts-logits-general · gemini-2.0-flash

    constructor calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zeptember
    -0.49
    Trusted
    -0.47
    globals
    -0.47
     voilà
    -0.46
    folger
    -0.46
     gesch
    -0.44
    ждествен
    -0.44
     Heim
    -0.44
     techs
    -0.44
    HAHAHAHA
    -0.44
    POSITIVE LOGITS
     متعلقه
    1.03
    webElement
    1.01
    MLLoader
    0.89
    DockStyle
    0.84
    tagHelperRunner
    0.81
    InstrumentedTest
    0.80
     hereinafter
    0.79
     shall
    0.79
     vallée
    0.74
    Geplaatst
    0.73
    Act Density 0.045%

    No Known Activations