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

    Neuronpedia

    INDEX
    Explanations

    Spanish/Portuguese

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     what
    -0.07
    工程
    -0.07
     tol
    -0.07
     July
    -0.07
    -ext
    -0.07
    Is
    -0.06
    (vec
    -0.06
    (reg
    -0.06
     levels
    -0.06
     Is
    -0.06
    POSITIVE LOGITS
    amos
    0.10
     мы
    0.10
    ходим
    0.09
     We
    0.09
    We
    0.09
     abbiamo
    0.09
     estamos
    0.09
     podemos
    0.08
    iamo
    0.08
    emos
    0.08
    Act Density 0.030%

    No Known Activations