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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence boundaries

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

    initial, patterns, round, know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.50
    amerikanischer
    -0.50
     ModelExpression
    -0.49
    IntoConstraints
    -0.49
    +#+
    -0.48
    AndEndTag
    -0.46
    FunctionFlags
    -0.45
    存于互联网档案馆
    -0.45
    reportWebVitals
    -0.45
    RTCK
    -0.44
    POSITIVE LOGITS
    queryInterface
    0.41
     Photocase
    0.38
    hematics
    0.36
     geraten
    0.34
    atoga
    0.34
    StoryboardSegue
    0.34
     SIG
    0.33
    ₫
    0.32
    Now
    0.32
     xxvi
    0.31
    Act Density 0.053%

    No Known Activations