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

    Neuronpedia

    INDEX
    Explanations

    references to different levels of achievement or competence

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

    position or standard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     препратки
    -0.67
    windowFixed
    -0.57
     SwitchCompat
    -0.57
     ModelExpression
    -0.53
    lccn
    -0.52
    WebElementEntity
    -0.50
     المعيارى
    -0.49
    Demografie
    -0.48
     فريبيس
    -0.47
    MarshalTo
    -0.47
    POSITIVE LOGITS
     niveau
    0.60
    Niveau
    0.58
     level
    0.58
     Niveau
    0.57
    level
    0.57
    レベル
    0.54
     livello
    0.54
    Level
    0.53
     nível
    0.52
    niveau
    0.52
    Act Density 0.013%

    No Known Activations