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

    Neuronpedia

    INDEX
    Explanations

    occurrences of XML or HTML tags

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

    <start_of_turn> user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.93
    featureID
    -0.78
    principalTable
    -0.74
    didSet
    -0.71
    fromnode
    -0.71
    oneofs
    -0.66
    NameInMap
    -0.65
    IntOverflow
    -0.63
    SharedCtor
    -0.63
    InitVars
    -0.63
    POSITIVE LOGITS
     <
    0.91
     (<
    0.54
     $<
    0.50
    (<
    0.49
    <
    0.47
     [
    0.44
     '<
    0.42
    。<
    0.42
     important
    0.42
    ;<
    0.41
    Act Density 0.004%

    No Known Activations