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

    Neuronpedia

    INDEX
    Explanations

    occurrences of messages or message-related terms in a context, particularly in code or text

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

    system message

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    habits
    -0.42
    ❉
    -0.41
     Mathf
    -0.40
     useRef
    -0.39
     useRouter
    -0.39
     remo
    -0.37
    这款
    -0.37
    moveToNext
    -0.37
     MOB
    -0.35
    引き続き
    -0.35
    POSITIVE LOGITS
    makeText
    0.69
     mensaje
    0.63
     message
    0.62
    message
    0.59
     mensagem
    0.57
     messaggio
    0.56
    RenderAtEndOf
    0.55
    MESSAGE
    0.54
    setMessage
    0.52
     messages
    0.51
    Act Density 0.023%

    No Known Activations