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

    Neuronpedia

    INDEX
    Explanations

    expressions of dissatisfaction or disappointment

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

    progressive ideals and dissatisfaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     habit
    -0.28
    bottomrule
    -0.28
    Avoid
    -0.28
    saraba
    -0.27
    Inter
    -0.25
    던
    -0.25
     avoid
    -0.25
     unique
    -0.25
     NEW
    -0.24
     Inter
    -0.24
    POSITIVE LOGITS
    featureID
    0.74
     BoxFit
    0.73
    MLLoader
    0.68
    RenderAtEndOf
    0.67
     propOrder
    0.66
    archiviato
    0.66
     ब्रेकडाउन
    0.63
    AddTagHelper
    0.63
    ésultats
    0.63
    ChildScrollView
    0.61
    Act Density 0.111%

    No Known Activations