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

    Neuronpedia

    INDEX
    Explanations

    fusion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     absolut
    -0.08
    лід
    -0.08
     터
    -0.07
     escala
    -0.07
    ీన
    -0.07
     확대
    -0.07
     неож
    -0.07
     کنند
    -0.07
    озя
    -0.07
     تحلیل
    -0.07
    POSITIVE LOGITS
     parms
    0.09
     hàng
    0.08
    James
    0.08
     Seite
    0.08
     James
    0.08
    .concat
    0.08
     bx
    0.08
     Mina
    0.08
     mi
    0.08
    Parms
    0.07
    Act Density 0.001%

    No Known Activations