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

    Neuronpedia

    INDEX
    Explanations

    references to various coding components and their imports in programming code

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

    import

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.90
     '\\;'
    -0.87
    <unused68>
    -0.72
    <unused41>
    -0.72
     resourceCulture
    -0.72
    <unused79>
    -0.72
    <unused14>
    -0.72
    <unused8>
    -0.72
    <unused3>
    -0.72
    [@BOS@]
    -0.72
    POSITIVE LOGITS
    parseColor
    0.27
    neq
    0.26
    or
    0.26
    ness
    0.26
     Szw
    0.25
    sap
    0.24
    s
    0.23
     or
    0.23
    en
    0.23
     êtres
    0.23
    Act Density 0.006%

    No Known Activations