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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks in various contexts

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

    HTML comments and code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.84
    IntoConstraints
    -0.80
    ✨:
    -0.77
    __(/*!
    -0.73
    -0.68
     للمعارف
    -0.68
     surla
    -0.66
     فريبيس
    -0.65
    Tikang
    -0.65
    Datuak
    -0.65
    POSITIVE LOGITS
     spéciaux
    0.39
     surtido
    0.37
     quedo
    0.36
     dichos
    0.36
     alguno
    0.36
     Ejecutivo
    0.36
     llego
    0.35
     spéciale
    0.33
     llena
    0.33
     lección
    0.33
    Act Density 0.202%

    No Known Activations