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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and structures

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

    code-like strings and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wireType
    -0.49
     تانيه
    -0.38
    jira
    -0.35
    LoadScene
    -0.33
    inhua
    -0.33
    ↹
    -0.32
    ₁(
    -0.32
    obi
    -0.32
    bine
    -0.32
     SUDOC
    -0.32
    POSITIVE LOGITS
     $
    0.60
     Mr
    0.59
    uxxxx
    0.56
    :✨
    0.51
    Дереккөздер
    0.50
    aarrggbb
    0.49
    rungsseite
    0.49
    RectangleBorder
    0.48
     Италијани
    0.47
     surla
    0.47
    Act Density 0.006%

    No Known Activations