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

    Neuronpedia

    INDEX
    Explanations

    URLs and web-related formatting elements

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

    Text following "Q:" or "import"

    np_acts-logits-general · gemini-2.0-flash

    questions and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.65
     (
    -0.62
    -
    -0.62
    ,
    -0.61
     I
    -0.61
    ValueStyle
    -0.60
    1
    -0.59
     W
    -0.58
    ViewImports
    -0.55
     to
    -0.55
    POSITIVE LOGITS
     houſe
    1.10
    ſelves
    1.03
     faſt
    1.02
    ſelf
    1.01
     Majefty
    1.01
     purpoſe
    1.00
     ſtate
    0.99
     Houſe
    0.99
     ſmall
    0.95
     ſche
    0.95
    Act Density 0.454%

    No Known Activations