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

    Neuronpedia

    INDEX
    Explanations

    unusual formatting or whitespace patterns in the text

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

    Followed by a number

    np_acts-logits-general · gemini-2.0-flash

    multiple languages or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Портал
    -0.68
    InjectAttribute
    -0.68
    atguigu
    -0.61
    معلومات
    -0.60
    achio
    -0.60
    onAttach
    -0.59
    трите
    -0.59
    Personendaten
    -0.58
    Portail
    -0.57
    Gdx
    -0.56
    POSITIVE LOGITS
    MessageOf
    0.56
    </blockquote>
    0.56
     disambiguazione
    0.51
    User
    0.48
    ">//
    0.46
     kuin
    0.45
    Sucesor
    0.45
     sweats
    0.44
     rejoined
    0.43
    Dacă
    0.42
    Act Density 0.013%

    No Known Activations