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

    Neuronpedia

    INDEX
    Explanations

    value propositions, value streams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    D
    1.09
    B
    1.04
    К
    1.01
    M
    1.00
    ל
    0.98
    F
    0.97
    G
    0.97
    K
    0.97
    H
    0.95
    C
    0.95
    POSITIVE LOGITS
     toneladas
    1.13
     sofern
    1.02
     traje
    0.98
     situado
    0.98
     vicenda
    0.98
     mejorar
    0.97
     retomar
    0.97
     seguros
    0.96
     yattha
    0.96
     otorg
    0.96
    Act Density 0.001%

    No Known Activations