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

    Neuronpedia

    INDEX
    Explanations

    Pope related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ihren
    -0.08
     Silva
    -0.08
     Để
    -0.08
    SelfPermission
    -0.07
     servidor
    -0.07
     Ihrem
    -0.07
    接种
    -0.07
    (textBox
    -0.07
     Civic
    -0.06
    いただいて
    -0.06
    POSITIVE LOGITS
    헬
    0.07
    остью
    0.07
     disagreements
    0.06
    Prefs
    0.06
     foes
    0.06
     raging
    0.06
    Row
    0.06
     devastation
    0.06
    凯
    0.06
     troublesome
    0.06
    Act Density 0.018%

    No Known Activations