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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically periods and semicolons

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

    java package namespaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     navideña
    -0.48
     Italij
    -0.42
    原始内容存档于
    -0.42
     chóng
    -0.42
    ConstraintMaker
    -0.40
     exposición
    -0.39
     Económica
    -0.38
     costumbre
    -0.38
     conclusión
    -0.38
     Betreuung
    -0.38
    POSITIVE LOGITS
     Italijanski
    0.66
     <<<<<<<<<<<<<<
    0.57
    oa̍t
    0.55
    parsedMessage
    0.54
    expandindo
    0.54
    setVerticalGroup
    0.53
    endcsname
    0.52
     ivelany
    0.52
     Chwiliwch
    0.50
     gynhyrchwyd
    0.49
    Act Density 0.005%

    No Known Activations