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

    Neuronpedia

    INDEX
    Explanations

    names associated with fashion and film promotion

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

    academic and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.38
     uParam
    -0.34
    Settings
    -0.34
     Ternyata
    -0.34
     Estas
    -0.34
     penge
    -0.33
    WebElement
    -0.32
    settings
    -0.32
    Retention
    -0.32
     intervención
    -0.32
    POSITIVE LOGITS
    ########.
    0.68
    ukone
    0.68
     EconPapers
    0.58
     мәкал
    0.57
     iNdEx
    0.55
    Diweddarwch
    0.55
    awtextra
    0.54
    matchCondition
    0.51
     MenuView
    0.50
    verifyException
    0.48
    Act Density 0.026%

    No Known Activations