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

    Neuronpedia

    INDEX
    Explanations

    significant statistical values or markers in scientific data analysis

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

    section titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Савезне
    -0.72
    GEBURTSDATUM
    -0.62
    rungsseite
    -0.62
    WaitGroup
    -0.60
    səhifə
    -0.60
    ModelAdmin
    -0.59
     Roskov
    -0.58
    InjectAttribute
    -0.54
    AndEndTag
    -0.54
     
    -0.53
    POSITIVE LOGITS
    \{\\
    0.49
    foundation
    0.47
    nullptr
    0.44
    anchor
    0.43
    birth
    0.41
    atmosfera
    0.40
    desc
    0.40
     deği
    0.40
     dirigir
    0.39
    ByIndex
    0.39
    Act Density 0.004%

    No Known Activations