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

    Neuronpedia

    INDEX
    Explanations

    sequences of special characters or symbols, particularly those commonly used in coding or formatting

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

    URLs and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ymce
    -0.43
    oncesto
    -0.35
     indicted
    -0.35
    matchCondition
    -0.35
     above
    -0.35
    DebuggerNonUser
    -0.34
     MUM
    -0.34
     below
    -0.33
     Calle
    -0.32
    面
    -0.32
    POSITIVE LOGITS
    MessageOf
    0.75
    CopyWith
    0.66
     للمعارف
    0.66
    {§
    0.63
     <<<<<<<<<<<<<<
    0.58
    オク
    0.56
    msgTypes
    0.56
     '\\;'
    0.56
     EconPapers
    0.56
    protoimpl
    0.55
    Act Density 0.272%

    No Known Activations