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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ера
    -0.07
    -section
    -0.07
    ,a
    -0.07
     stands
    -0.07
     comma
    -0.07
     яв
    -0.06
    channel
    -0.06
     winding
    -0.06
     rollers
    -0.06
    -st
    -0.06
    POSITIVE LOGITS
     of
    0.08
    -of
    0.07
     ceux
    0.07
     at
    0.07
     getTotal
    0.07
    xbf
    0.06
     EDUC
    0.06
     lot
    0.06
    档
    0.06
     incididunt
    0.06
    Act Density 0.062%

    No Known Activations