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

    Neuronpedia

    INDEX
    Explanations

    terms related to programming constructs and identifiers in code

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

    error codes and IDs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.57
    ValueStyle
    -0.50
     dificultad
    -0.50
     Comprometido
    -0.49
    Tembelea
    -0.49
     complejidad
    -0.48
     autorytatywna
    -0.47
     incompatibility
    -0.47
    annica
    -0.47
    揄
    -0.46
    POSITIVE LOGITS
    吹き
    0.37
    fle
    0.35
    expandindo
    0.35
     kasarigan
    0.35
     нена
    0.35
    ling
    0.34
    ram
    0.34
    PO
    0.33
    {}
    0.33
    luft
    0.32
    Act Density 0.096%

    No Known Activations