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

    Neuronpedia

    INDEX
    Explanations

    C++ syntax used for input and output operations

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

    C++ code snippets and error messages

    np_acts-logits-general · gemini-2.0-flash

    a Minor-based Change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tembelea
    -0.73
    लय
    -0.60
    Portail
    -0.59
    principalColumn
    -0.59
    \{\\
    -0.59
    aarrggbb
    -0.56
    oredCriteria
    -0.55
    __(/*!
    -0.54
    Geplaatst
    -0.54
    ymce
    -0.52
    POSITIVE LOGITS
     endl
    1.17
    endl
    1.16
    flush
    0.63
    ends
    0.62
     flush
    0.61
     fixed
    0.60
    fixed
    0.58
     dec
    0.56
     Fixed
    0.56
     seti
    0.55
    Act Density 0.101%

    No Known Activations