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

    Neuronpedia

    INDEX
    Explanations

    terms related to data processing and optimization algorithms

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

    computation and decision-making

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.91
    PostInfinity
    -0.73
    tagHelperRunner
    -0.73
    LookAnd
    -0.72
    <unused1>
    -0.70
     otomatig
    -0.70
     $_=
    -0.70
     tartalo
    -0.70
    <unused74>
    -0.70
    <unused8>
    -0.70
    POSITIVE LOGITS
     precisely
    0.27
     Erzb
    0.24
     later
    0.23
     LoggerFactory
    0.23
    ườn
    0.23
    +#+#
    0.23
    in
    0.23
     masuk
    0.22
     again
    0.21
     dazu
    0.21
    Act Density 0.451%

    No Known Activations