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

    Neuronpedia

    INDEX
    Explanations

    occurrences of numeric values or counts

    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
     kaarangay
    -0.54
    ftagPool
    -0.50
     Савезне
    -0.47
     незавершена
    -0.46
    PyExc
    -0.44
    硃
    -0.43
    ↻
    -0.43
    Rptr
    -0.42
    getLogger
    -0.42
    存于互联网档案馆
    -0.42
    POSITIVE LOGITS
    AxisAlignment
    0.54
    SequentialGroup
    0.46
    NOPQRST
    0.45
     ſte
    0.44
    ništvo
    0.41
     ſtate
    0.40
    geführten
    0.40
    ſelf
    0.40
    BeginInit
    0.39
    TagHelper
    0.39
    Act Density 0.002%

    No Known Activations