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

    Neuronpedia

    INDEX
    Explanations

    flowers and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    е
    0.64
    การ
    0.61
    들이
    0.61
     cinéma
    0.60
     agua
    0.59
     segurança
    0.57
     halftime
    0.57
     स्थिति
    0.56
    і
    0.56
     gale
    0.55
    POSITIVE LOGITS
    r
    0.72
    paste
    0.66
    ized
    0.66
    ر
    0.64
    flowers
    0.61
    花
    0.61
    花的
    0.60
    ip
    0.59
    flower
    0.57
     emitted
    0.55
    Act Density 0.005%

    No Known Activations