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

    Neuronpedia

    INDEX
    Explanations

    the concept of universality across different contexts

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

    universal concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Meksi
    -0.50
    躇
    -0.46
    borderSide
    -0.42
     Turquía
    -0.41
     Venedig
    -0.41
     Irán
    -0.40
     Moscú
    -0.40
     Fotografía
    -0.39
     venezolano
    -0.38
     tuples
    -0.38
    POSITIVE LOGITS
     universal
    2.17
    universal
    2.02
     Universal
    1.85
    Universal
    1.80
     UNIVERSAL
    1.75
     universale
    1.61
     universality
    1.52
     universel
    1.51
     universally
    1.48
     universelle
    1.42
    Act Density 0.006%

    No Known Activations