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

    Neuronpedia

    INDEX
    Explanations

    programming functions and operations, especially those involving collections and their manipulations

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

    list mapping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    发表于
    -0.39
    wsj
    -0.35
    mfg
    -0.34
     Sociales
    -0.33
     Gol
    -0.33
     omkring
    -0.33
     briefs
    -0.32
     videre
    -0.32
    isRequired
    -0.32
    addTo
    -0.31
    POSITIVE LOGITS
     Administrativna
    0.75
    الحياه
    0.70
     Савезне
    0.64
     pinulongan
    0.63
     sumpay
    0.57
    ValueStyle
    0.56
    WebVitals
    0.55
    CloseOperation
    0.54
    Jereo
    0.54
    IsMutable
    0.54
    Act Density 0.007%

    No Known Activations