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

    Neuronpedia

    INDEX
    Explanations

    high numerical values in a data context

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

    hexadecimal identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.67
    httphttps
    -0.67
    AddTagHelper
    -0.65
    -0.63
     Wiktionnaire
    -0.63
    뀜
    -0.62
    matchCondition
    -0.62
    styleType
    -0.60
     iprot
    -0.60
    ThemeOverlay
    -0.60
    POSITIVE LOGITS
     f
    0.64
     getF
    0.62
     F
    0.59
    F
    0.55
    fi
    0.55
     FLO
    0.50
    f
    0.49
    fc
    0.49
     fname
    0.48
     FANT
    0.47
    Act Density 0.071%

    No Known Activations