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

    Neuronpedia

    INDEX
    Explanations

    plant descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    routes
    -0.07
    绍
    -0.07
    blend
    -0.07
    cam
    -0.06
     dear
    -0.06
     Gauge
    -0.06
    Discount
    -0.06
     �
    -0.06
    Suppress
    -0.06
    (ad
    -0.06
    POSITIVE LOGITS
    äsent
    0.07
     ;;↵
    0.07
    "};↵↵
    0.06
     çalışma
    0.06
     }}"><
    0.06
    ;↵↵
    0.06
    bsp
    0.06
    :↵
    0.06
     вико
    0.06
     ден
    0.06
    Act Density 0.030%

    No Known Activations