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

    Neuronpedia

    INDEX
    Explanations

    expressions of assistance or support

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

    help, advice, or evaluation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Vidite
    -0.69
     Taktlose
    -0.67
    RTEE
    -0.67
    MigrationBuilder
    -0.63
    :✨
    -0.63
     queſta
    -0.59
    出版年
    -0.58
    OGND
    -0.58
    mitian
    -0.58
    ьажоргаш
    -0.57
    POSITIVE LOGITS
    Cordialement
    0.40
    !
    0.36
    Linki
    0.35
     couverts
    0.33
     Consultez
    0.31
     leading
    0.30
    オリン
    0.30
     therefore
    0.29
    TextEditing
    0.29
    MessageTagHelper
    0.29
    Act Density 0.025%

    No Known Activations