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

    Neuronpedia

    INDEX
    Explanations

    the abbreviation "HL" followed by varying numerical identifiers

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

    hl followed by equals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TemporalType
    -0.55
     useState
    -0.51
    createCanvas
    -0.50
    ynb
    -0.50
     Schmitz
    -0.49
     McCulloch
    -0.48
    mergeFrom
    -0.48
     Fleisch
    -0.48
    subpackage
    -0.47
    putExtra
    -0.46
    POSITIVE LOGITS
    hl
    2.73
    HL
    2.08
     hl
    1.70
     HL
    1.66
    Hl
    1.29
     Hl
    1.23
    hls
    1.13
    hli
    1.12
    hla
    1.09
    AHL
    1.08
    Act Density 0.017%

    No Known Activations