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

    Neuronpedia

    INDEX
    Explanations

    forget quick, vague, loud

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     VERY
    0.44
    )[
    0.39
    非
    0.39
     non
    0.38
     both
    0.38
    Non
    0.38
     nontrivial
    0.36
    Очень
    0.36
     approximately
    0.36
     very
    0.36
    POSITIVE LOGITS
     tradicionales
    0.80
    传统的
    0.79
     tradicional
    0.79
     conventional
    0.76
     tradicion
    0.73
    傳統
    0.71
     flashy
    0.70
     tradizionale
    0.70
     traditionnel
    0.70
    従来の
    0.70
    Act Density 0.120%

    No Known Activations