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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating duality or choices in life

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

    sentence-ending words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     corriendo
    -0.29
    harapkan
    -0.27
     voks
    -0.26
    dataTables
    -0.26
    EPC
    -0.25
     drapeau
    -0.25
     PublicKey
    -0.24
    IonicModule
    -0.24
    WebpackPlugin
    -0.24
    ーンズ
    -0.24
    POSITIVE LOGITS
     EconPapers
    0.83
    VersionUID
    0.81
    +#+#
    0.76
     nahilalakip
    0.71
     arşivlendi
    0.69
    Personensuche
    0.68
    SequentialGroup
    0.63
     Мексичка
    0.63
    жнему
    0.62
    AutoField
    0.61
    Act Density 0.153%

    No Known Activations