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

    Neuronpedia

    INDEX
    Explanations

    references to specific entries or detailed information

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

    names, sizes, lists, examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.66
    tagHelperRunner
    -0.56
    ApiModelProperty
    -0.54
    WarningLevel
    -0.52
    izoen
    -0.48
    orit
    -0.47
    styleable
    -0.47
     nahilalakip
    -0.47
     angus
    -0.46
     Provid
    -0.46
    POSITIVE LOGITS
     lecciones
    0.45
     ciertamente
    0.45
     насељу
    0.44
    seguida
    0.42
     corrientes
    0.41
     lección
    0.41
     asimismo
    0.41
     moviliz
    0.41
     peores
    0.40
     oscuridad
    0.39
    Act Density 0.078%

    No Known Activations