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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Yaw
    -0.08
     seinen
    -0.07
     Tenant
    -0.07
    His
    -0.06
     Lịch
    -0.06
    сторія
    -0.06
    .Our
    -0.06
     vest
    -0.06
     WooCommerce
    -0.06
    odí
    -0.06
    POSITIVE LOGITS
     clamp
    0.07
    سه
    0.07
    晚
    0.06
    832
    0.06
     unlocks
    0.06
    AMPL
    0.06
    .reduce
    0.06
     госп
    0.06
    .close
    0.06
    711
    0.06
    Act Density 0.006%

    No Known Activations