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

    Neuronpedia

    INDEX
    Explanations

    names and references to individuals of Indian descent

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

    names and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Хьажоргаш
    -0.60
    Personendaten
    -0.55
    aarrggbb
    -0.53
    argout
    -0.53
    TestingModule
    -0.51
     препратки
    -0.51
     
    -0.50
     BoxFit
    -0.50
    
    -0.49
     للاسماء
    -0.49
    POSITIVE LOGITS
    weif
    0.41
     Begründung
    0.40
     Wirtschafts
    0.39
     tradisi
    0.39
     Reised
    0.38
     Ecke
    0.38
    Quién
    0.38
     lecciones
    0.38
     Vorles
    0.37
    Fondo
    0.37
    Act Density 0.270%

    No Known Activations