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

    Neuronpedia

    INDEX
    Explanations

    phrases indicative of database or code-related operations

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

    non-degenerate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    QRect
    -0.65
    shadowOpacity
    -0.61
    MethodManager
    -0.60
    setVerticalGroup
    -0.60
    awtextra
    -0.59
     nonUne
    -0.58
    isSuccessful
    -0.57
    ◚
    -0.57
     initWithFrame
    -0.57
    parsedMessage
    -0.57
    POSITIVE LOGITS
    citos
    0.35
    Ligações
    0.34
     suela
    0.33
     helft
    0.32
     Vereinbarung
    0.31
    Autoritní
    0.30
     pagrind
    0.29
     direkte
    0.29
     simak
    0.29
     głó
    0.29
    Act Density 0.000%

    No Known Activations