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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Flu
    -0.07
    /jpeg
    -0.07
     vg
    -0.07
    ביצ
    -0.07
    �
    -0.07
     נשמע
    -0.06
     Gn
    -0.06
    ⛇
    -0.06
    艮
    -0.06
     !(
    -0.06
    POSITIVE LOGITS
     plan
    0.07
     ICMP
    0.07
    heure
    0.07
     sequentially
    0.07
     nond
    0.07
     Responsible
    0.07
    price
    0.06
    优惠政策
    0.06
     predetermined
    0.06
     rule
    0.06
    Act Density 0.036%

    No Known Activations