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

    Neuronpedia

    INDEX
    Explanations

    terms related to cell phone etiquette and rules of use

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

    Rules or prohibitions

    np_acts-logits-general · gemini-2.0-flash

    rules and permissions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     referenties
    -0.87
     AssemblyCulture
    -0.73
     nahilalakip
    -0.69
    fjspx
    -0.66
    writeFieldEnd
    -0.64
     estimés
    -0.61
     '\\;'
    -0.57
    éez
    -0.56
    astéroïdes
    -0.55
     <>",
    -0.52
    POSITIVE LOGITS
     prohibited
    0.91
     permitted
    0.85
     pets
    0.72
     unattended
    0.72
     allowed
    0.72
     permitido
    0.71
     unauthorized
    0.70
     visitors
    0.70
     unsupervised
    0.70
    ALLOWED
    0.68
    Act Density 0.229%

    No Known Activations