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

    Neuronpedia

    INDEX
    Explanations

    negative sentiment or unfavorable characteristics

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

    uuid identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AsUp
    -0.80
     AssemblyCulture
    -0.78
     faſt
    -0.77
    LookAnd
    -0.77
     Houſe
    -0.74
    AddTagHelper
    -0.72
    ſelf
    -0.71
     pleaſure
    -0.70
     ſon
    -0.69
    webElementXpaths
    -0.67
    POSITIVE LOGITS
    -
    0.56
    –
    0.47
     -
    0.44
    -\
    0.40
    }-
    0.40
    ("-
    0.36
     van
    0.35
    .-
    0.35
    }-\
    0.35
     Wal
    0.35
    Act Density 0.079%

    No Known Activations