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

    Neuronpedia

    INDEX
    Explanations

    structured information and hierarchical organization in documents

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

    Text following titles or introductions

    np_acts-logits-general · gemini-2.0-flash

    section headings and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    saraba
    -0.81
     typelib
    -0.79
     المعيارى
    -0.78
    stdc
    -0.71
    tagHelper
    -0.67
    Revenir
    -0.66
    EndContext
    -0.66
    mybatisplus
    -0.64
    DECREF
    -0.64
     Wikimedijinoj
    -0.64
    POSITIVE LOGITS
     This
    0.81
    This
    0.81
    There
    0.76
    The
    0.75
     There
    0.73
    When
    0.72
     The
    0.70
     When
    0.68
     We
    0.66
     Although
    0.64
    Act Density 0.934%

    No Known Activations