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

    Neuronpedia

    INDEX
    Explanations

    Inspecting for damage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Slight
    -0.08
     puisque
    -0.08
     systemen
    -0.08
     puisqu
    -0.08
    ánd
    -0.08
    ಾಯಿತು
    -0.08
     प्रण
    -0.07
    олю
    -0.07
    ları
    -0.07
     Starting
    -0.07
    POSITIVE LOGITS
     vergang
    0.09
     pitk
    0.08
    進
    0.08
     historial
    0.08
    omne
    0.08
     কোন
    0.08
     хара
    0.07
     ұз
    0.07
     progress
    0.07
    cesse
    0.07
    Act Density 0.007%

    No Known Activations