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

    Neuronpedia

    INDEX
    Explanations

    debugging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ventana
    -0.07
    You
    -0.07
    شرط
    -0.07
    圣诞节
    -0.07
    כנסת
    -0.06
    ="$(
    -0.06
    CAC
    -0.06
    uyến
    -0.06
     Tout
    -0.06
    ENT
    -0.06
    POSITIVE LOGITS
    _led
    0.08
     jsx
    0.07
    herited
    0.07
    (java
    0.07
     brakes
    0.07
     atmosphere
    0.07
    社会治理
    0.07
     пользоват
    0.06
    jure
    0.06
    preh
    0.06
    Act Density 0.009%

    No Known Activations