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

    Neuronpedia

    INDEX
    Explanations

    calls to action and requests for user engagement

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

    Preceding verbs like "find", "see", "read", "Learn", etc

    np_acts-logits-general · gemini-2.0-flash

    finding and seeing more information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Besøkt
    -0.61
    EDEFAULT
    -0.60
     mergeFrom
    -0.59
     '\\;'
    -0.58
    DrawerToggle
    -0.57
    -0.56
    Diweddarwch
    -0.55
    principalTable
    -0.55
    TargetException
    -0.55
    ImageContext
    -0.54
    POSITIVE LOGITS
     übrigens
    0.54
    "])
    0.54
     maggiori
    0.54
     current
    0.53
    ()])
    0.53
     »)
    0.52
    ggior
    0.51
    engkapnya
    0.51
    ']));
    0.50
    .")]
    0.50
    Act Density 0.149%

    No Known Activations