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

    Neuronpedia

    INDEX
    Explanations

    different forms of parentheses and related syntax in code

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

    macro definitions with bit shifts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.84
    يكب
    -0.81
    rizona
    -0.75
    ItemBackground
    -0.63
     препратки
    -0.63
     vPvB
    -0.62
    خواندن
    -0.61
     sexuales
    -0.61
    rrggbb
    -0.60
     complètes
    -0.60
    POSITIVE LOGITS
    rungsseite
    0.77
     (
    0.62
     ((
    0.56
    Revenir
    0.51
     fort
    0.50
    SequentialGroup
    0.50
     Fort
    0.50
     port
    0.49
    vanni
    0.49
     +(
    0.49
    Act Density 0.022%

    No Known Activations