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

    Neuronpedia

    INDEX
    Explanations

    R

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    יטב
    -0.07
     mesmo
    -0.07
    맆
    -0.07
    惆
    -0.07
    tcp
    -0.07
     Ou
    -0.06
    😽
    -0.06
    .cl
    -0.06
    tuple
    -0.06
    Knowing
    -0.06
    POSITIVE LOGITS
    groupon
    0.07
     contrib
    0.07
    chers
    0.07
     מבלי
    0.07
     fortunate
    0.07
     GC
    0.06
    ьер
    0.06
     Drill
    0.06
    燹
    0.06
    lesson
    0.06
    Act Density 0.001%

    No Known Activations