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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols, especially periods and underscores

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

    JSON stringify and parse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    8
    -0.44
    4
    -0.43
    3
    -0.40
    5
    -0.37
    いる
    -0.37
    2
    -0.34
    reuung
    -0.32
    with
    -0.32
    using
    -0.32
    مند
    -0.31
    POSITIVE LOGITS
     autorytatywna
    0.90
    exitRule
    0.72
     utafitiHapana
    0.71
    iſen
    0.70
     GetEnumerator
    0.66
     defaultstate
    0.66
     BoxFit
    0.65
    IntoConstraints
    0.65
     Италијани
    0.64
    ByVersion
    0.64
    Act Density 0.002%

    No Known Activations