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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exceptionalism or distinction

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

    roles and classifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.60
    UrlResolution
    -0.56
     nakalista
    -0.54
    JspWriter
    -0.50
    featureID
    -0.50
    contentLoaded
    -0.49
    SharedDtor
    -0.47
    DockStyle
    -0.47
    WriteTagHelper
    -0.47
     NSCoder
    -0.47
    POSITIVE LOGITS
     cumplido
    0.51
     pendukung
    0.43
     يتيمه
    0.43
     adopción
    0.41
     pandangan
    0.41
     coscienza
    0.41
     prática
    0.40
     ligação
    0.40
    팎
    0.39
    pertina
    0.39
    Act Density 0.100%

    No Known Activations