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

    Neuronpedia

    INDEX
    Explanations

    ely

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .addTab
    -0.08
     вог
    -0.07
     nemůže
    -0.07
     fetus
    -0.06
     centroids
    -0.06
     mělo
    -0.06
    .sqrt
    -0.06
    Alternative
    -0.06
     (↵↵
    -0.06
     pus
    -0.06
    POSITIVE LOGITS
     Merkel
    0.08
    mn
    0.08
     unt
    0.07
     goal
    0.07
    !="
    0.06
     λι
    0.06
     відб
    0.06
    千
    0.06
     �
    0.06
    sched
    0.06
    Act Density 0.002%

    No Known Activations