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

    Neuronpedia

    INDEX
    Explanations

    terms related to concepts of "normalcy" and "standardization."

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

    following "normal" or "standard"

    np_acts-logits-general · gemini-2.0-flash

    normal state and process

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.79
     específico
    -0.71
     متعلقه
    -0.71
     specifically
    -0.69
     spécifique
    -0.66
     específicamente
    -0.63
     חיצוניים
    -0.63
     spécifiques
    -0.63
    ANTLR
    -0.62
     spéciale
    -0.62
    POSITIVE LOGITS
    isation
    0.98
    izing
    0.93
     suspects
    0.92
    izations
    0.82
    izers
    0.82
     fare
    0.81
    izes
    0.79
     bearers
    0.78
    izer
    0.78
     sized
    0.78
    Act Density 0.234%

    No Known Activations