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

    Neuronpedia

    INDEX
    Explanations

    code related to class and component definitions in programming

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

    Code or data fragments

    np_acts-logits-general · gemini-2.0-flash

    Project definitions and C-style macros

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    发表于
    -0.40
    انجليز
    -0.35
     bénéfice
    -0.34
    MENAFN
    -0.32
    initComponents
    -0.31
     שוליים
    -0.31
    __;
    -0.29
     så
    -0.28
     Deckel
    -0.27
     says
    -0.26
    POSITIVE LOGITS
    aarrggbb
    0.66
    <unused74>
    0.59
    <unused8>
    0.59
    <unused68>
    0.59
    <unused28>
    0.58
    <unused3>
    0.58
    <unused41>
    0.58
    <unused52>
    0.58
    <pad>
    0.58
    [@BOS@]
    0.58
    Act Density 0.638%

    No Known Activations