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

    Neuronpedia

    INDEX
    Explanations

    assertive statements and expressions of opinion or belief

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

    yes, followed by confirmation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.48
    lichung
    -0.44
    GetMapping
    -0.43
     GoogleFonts
    -0.43
    jsxFileName
    -0.41
    CreateModel
    -0.41
    Concept
    -0.41
    이션
    -0.40
    يميديا
    -0.40
    inalg
    -0.39
    POSITIVE LOGITS
     yes
    0.69
    Yes
    0.66
     Yes
    0.65
    yes
    0.58
     YES
    0.50
    是的
    0.48
    ++){
    0.47
     نعم
    0.47
    YES
    0.47
     כן
    0.46
    Act Density 0.045%

    No Known Activations