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

    Neuronpedia

    INDEX
    Explanations

    mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    точ
    -0.08
     lembrar
    -0.07
     Remember
    -0.07
    remember
    -0.07
    йте
    -0.07
    inho
    -0.07
    fmt
    -0.07
     avo
    -0.07
     weich
    -0.07
    iefer
    -0.07
    POSITIVE LOGITS
    ，否则
    0.11
     necessarily
    0.09
     necesariamente
    0.09
    Eventually
    0.08
    necessarily
    0.08
    ంలోని
    0.08
     preservatives
    0.08
     entro
    0.08
    (document
    0.08
     بعدها
    0.08
    Act Density 0.079%

    No Known Activations