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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values and their significance within a context

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

    Text after numbers or symbols

    np_acts-logits-general · gemini-2.0-flash

    one to model execution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PyExc
    -0.41
    centralwidget
    -0.36
     onBackPressed
    -0.34
    EndContext
    -0.34
    RefNanny
    -0.34
    yyb
    -0.32
     jdbcTemplate
    -0.32
    TeV
    -0.32
     break
    -0.31
     WARN
    -0.31
    POSITIVE LOGITS
    Autoritní
    0.64
    ंदीखरीदारी
    0.63
    انتهای
    0.59
    findpost
    0.57
     تضيفلها
    0.57
    niająca
    0.56
    RTCK
    0.56
    édrale
    0.54
     zoude
    0.54
    pexpr
    0.53
    Act Density 1.081%

    No Known Activations