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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     分享
    -0.08
     सुंदर
    -0.08
     intercept
    -0.08
     सुविधा
    -0.07
     सबसे
    -0.07
     Convenience
    -0.07
     Año
    -0.07
     Utility
    -0.07
     poti
    -0.07
     propor
    -0.07
    POSITIVE LOGITS
     كلمة
    0.09
     tenzij
    0.08
     auft
    0.08
     및
    0.08
    xce
    0.08
    xdd
    0.08
    unless
    0.08
    は禁止
    0.08
    avoid
    0.07
     مشر
    0.07
    Act Density 0.001%

    No Known Activations