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

    Neuronpedia

    INDEX
    Explanations

    general text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cómo
    -0.07
    _AS
    -0.06
    perl
    -0.06
     sólo
    -0.06
    Cómo
    -0.06
     ROUND
    -0.06
     drove
    -0.06
     göz
    -0.06
    draw
    -0.06
    -floor
    -0.06
    POSITIVE LOGITS
     embeddings
    0.07
              ↵
    0.07
     ран
    0.06
     Salem
    0.06
    (False
    0.06
    νε
    0.06
     Inspection
    0.06
                    ↵
    0.06
     jej
    0.06
    alue
    0.06
    Act Density 0.000%

    No Known Activations