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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    forums
    -0.09
    lots
    -0.09
     Comunicación
    -0.08
     judicia
    -0.08
    ervers
    -0.08
     Communication
    -0.08
     Heard
    -0.08
    udis
    -0.08
     sermons
    -0.08
     Relation
    -0.08
    POSITIVE LOGITS
     crescente
    0.09
     Rails
    0.09
     creciente
    0.08
     pomp
    0.08
     quadratic
    0.08
     bunt
    0.07
     crec
    0.07
    რდება
    0.07
    ლება
    0.07
    渐
    0.07
    Act Density 0.020%

    No Known Activations