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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate actions, conditions, or emotions

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

    call or lawyer. When

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    noons
    -0.52
     kaynağından
    -0.51
    faßt
    -0.47
     decim
    -0.47
    ocities
    -0.47
    rawd
    -0.46
    WebServlet
    -0.46
    majánló
    -0.45
     disponibilités
    -0.45
    vorschaubild
    -0.45
    POSITIVE LOGITS
    Autoritní
    0.41
    diğini
    0.40
    outState
    0.37
    Diwedd
    0.35
    tagHelperRunner
    0.34
    LEGGI
    0.33
     виправивши
    0.32
    ChildScrollView
    0.32
     <<<<<<<<<<<<<<
    0.32
     μη
    0.32
    Act Density 0.075%

    No Known Activations