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

    Neuronpedia

    INDEX
    Explanations

    build walls, bricks as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    e
    0.74
     the
    0.63
     their
    0.63
    -
    0.57
    their
    0.55
    dis
    0.54
    Dis
    0.54
     pre
    0.51
    ing
    0.50
     dis
    0.50
    POSITIVE LOGITS
     emoción
    0.52
     ແລະ
    0.51
     ហើយ
    0.51
    蒌
    0.50
     takže
    0.49
     planificación
    0.49
     ကျွန်
    0.49
     escenario
    0.49
     descripción
    0.49
     verdad
    0.48
    Act Density 0.004%

    No Known Activations