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

    Neuronpedia

    INDEX
    Explanations

    references to copyright and usage permissions in documents

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

    isSelected in code context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.71
     Мексичка
    -0.67
    Personendaten
    -0.61
    MLLoader
    -0.61
    ########.
    -0.58
    GEBURTSDATUM
    -0.57
    хьтан
    -0.57
     Infórmanos
    -0.56
    AnimationsModule
    -0.53
    لينكات
    -0.52
    POSITIVE LOGITS
    isSelected
    0.46
    ปล
    0.39
    rawValue
    0.38
    Хьажоргаш
    0.38
    fromUtf
    0.37
    atelli
    0.37
     mấy
    0.36
     purchase
    0.36
    ://$
    0.36
    łów
    0.35
    Act Density 0.001%

    No Known Activations