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

    Neuronpedia

    INDEX
    Explanations

    numbered list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    code
    0.65
     yerine
    0.63
     postura
    0.63
     எழு
    0.60
    truth
    0.60
    version
    0.60
    context
    0.59
    स्थिति
    0.58
    state
    0.58
     ocorreu
    0.57
    POSITIVE LOGITS
     combos
    1.04
     pyramid
    1.01
     complementar
    0.99
     gems
    0.98
     Complement
    0.98
     sexy
    0.97
     즐
    0.96
     Favorites
    0.96
    ByCategory
    0.95
     Pyramid
    0.95
    Act Density 1.044%

    No Known Activations