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

    Neuronpedia

    INDEX
    Explanations

    references to alternatives or different options

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

    one and another

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addPreferredGap
    -0.74
     transfieras
    -0.60
    addGap
    -0.59
     CommandType
    -0.52
    webElementXpaths
    -0.52
     avoient
    -0.50
     Winaray
    -0.48
    UnusedPrivate
    -0.48
     soát
    -0.46
     CreateTagHelper
    -0.46
    POSITIVE LOGITS
    __":
    0.42
    indra
    0.40
    OGND
    0.39
    __':
    0.38
     bel
    0.38
    relsen
    0.38
    Bel
    0.37
    Havolalar
    0.36
    hiran
    0.36
     Sic
    0.36
    Act Density 0.143%

    No Known Activations