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

    Neuronpedia

    INDEX
    Explanations

    syntax elements or punctuation often found in programming code

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

    notes, code comments, or separator lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fahrung
    -0.38
     salvaje
    -0.38
    interopRequire
    -0.37
     caído
    -0.36
    CAPTURE
    -0.36
    asiswa
    -0.36
     pasukan
    -0.35
     dilan
    -0.35
     Flanagan
    -0.35
    CUT
    -0.35
    POSITIVE LOGITS
    ;;
    1.49
     ;;
    1.42
    ;;;
    1.05
    ;;;;
    0.85
    ;;)
    0.80
    );;
    0.76
     tartalomajánló
    0.69
     (;;
    0.69
    FieldNumber
    0.67
    :;
    0.66
    Act Density 0.005%

    No Known Activations