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

    Neuronpedia

    INDEX
    Explanations

    col

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cumhur
    -0.07
    747
    -0.06
     ประเทศ
    -0.06
     Barack
    -0.06
     Targets
    -0.06
     Rahul
    -0.06
     lifted
    -0.06
     Kingdom
    -0.06
    rons
    -0.06
     مردم
    -0.06
    POSITIVE LOGITS
    (console
    0.07
     coli
    0.07
    effect
    0.06
    =config
    0.06
     kız
    0.06
    -analysis
    0.06
    Collapsed
    0.06
    -commerce
    0.06
     showError
    0.06
     bev
    0.06
    Act Density 0.001%

    No Known Activations