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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and data structures in code snippets

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

    Hexadecimal code snippets

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal values or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OFDb
    -0.58
    AndEndTag
    -0.57
    SourceChecksum
    -0.52
    jgl
    -0.52
     ویکی‌پدی
    -0.51
    -0.50
    abestanden
    -0.50
    UserScript
    -0.50
     cref
    -0.50
    Datuak
    -0.48
    POSITIVE LOGITS
     same
    0.46
     mêmes
    0.41
     again
    0.41
    ۖ
    0.40
     Weltkrieg
    0.40
    ReusableCell
    0.40
     féd
    0.39
    })()
    0.38
    ufes
    0.37
     too
    0.35
    Act Density 0.235%

    No Known Activations