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

    Neuronpedia

    INDEX
    Explanations

    Perception and noticing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jums
    -0.08
     nuk
    -0.08
    <long
    -0.08
     вент
    -0.07
    ethode
    -0.07
     kòm
    -0.07
     whoever
    -0.07
    図
    -0.07
    ogolo
    -0.07
     sèche
    -0.07
    POSITIVE LOGITS
     atentos
    0.10
     捕
    0.09
     reconnaissance
    0.09
     novidades
    0.09
     vigilance
    0.09
    捕
    0.09
     kansen
    0.09
    识
    0.09
     herkennen
    0.09
     anyar
    0.09
    Act Density 0.015%

    No Known Activations