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

    Neuronpedia

    INDEX
    Explanations

    references to satisfaction, personal engagement, and certain numeric values or symbols

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

    crypt maximal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SuspendLayout
    -0.30
     “
    -0.30
    <em>
    -0.29
     Katze
    -0.29
    CppCodeGen
    -0.28
    <b>
    -0.27
    m
    -0.27
     Freiheit
    -0.27
    con
    -0.26
    <i>
    -0.26
    POSITIVE LOGITS
    <unused8>
    0.82
    <unused41>
    0.82
    <unused43>
    0.82
    <unused79>
    0.82
    <unused14>
    0.82
    [@BOS@]
    0.82
    <unused28>
    0.82
    <unused47>
    0.82
    <unused16>
    0.82
    <unused3>
    0.82
    Act Density 0.000%

    No Known Activations