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

    Neuronpedia

    INDEX
    Explanations

    patterns related to subscription or asynchronous communication in coding contexts

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

    programming keywords and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.81
     للمعارف
    -0.81
     utafitiHapana
    -0.76
    addCriterion
    -0.75
     ब्रेकडाउन
    -0.75
    InputBorder
    -0.73
    LookAnd
    -0.73
    transQ
    -0.73
    -0.72
    ValueStyle
    -0.69
    POSITIVE LOGITS
    ("""
    0.40
     Maria
    0.38
    """
    0.36
    Maria
    0.36
    string
    0.34
    …
    0.33
    String
    0.33
    J
    0.32
    AppendLine
    0.32
     "
    0.31
    Act Density 0.007%

    No Known Activations