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

    Neuronpedia

    INDEX
    Explanations

    UI elements and their attributes in a code context

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

    button class attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.77
     мәкал
    -0.70
    EndProject
    -0.68
    CppMethod
    -0.66
    tagHelperRunner
    -0.66
     NSCoder
    -0.64
    featureID
    -0.63
     utafitiHapana
    -0.62
    rungsseite
    -0.61
     Roskov
    -0.61
    POSITIVE LOGITS
     aimez
    0.31
    ,
    0.31
     uniformly
    0.30
    ™
    0.30
     ellos
    0.30
     ellas
    0.30
     Glaub
    0.30
    visel
    0.29
     niggas
    0.29
    wej
    0.28
    Act Density 0.015%

    No Known Activations