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

    Neuronpedia

    INDEX
    Explanations

    captured, prisoner

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vero
    -0.07
     Quar
    -0.06
     dép
    -0.06
     Alexandria
    -0.06
     Georgetown
    -0.06
    749
    -0.06
     Wiring
    -0.06
     Armstrong
    -0.06
    zw
    -0.06
    าสตร
    -0.06
    POSITIVE LOGITS
     inhal
    0.07
     العالمية
    0.06
     underwater
    0.06
     Plates
    0.06
    total
    0.06
    privacy
    0.06
     Deal
    0.06
    資料
    0.06
    (helper
    0.06
     inflict
    0.06
    Act Density 0.023%

    No Known Activations