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

    Neuronpedia

    INDEX
    Explanations

    academic/software standards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ৪
    -0.08
    skraft
    -0.08
     kinds
    -0.08
    ğı
    -0.07
     numbers
    -0.07
    �
    -0.07
    ة
    -0.07
     reins
    -0.07
     aptly
    -0.07
    (numbers
    -0.07
    POSITIVE LOGITS
     Synthetic
    0.09
     Multif
    0.09
     hagan
    0.08
     неоп
    0.08
     Scoped
    0.08
    ожет
    0.08
     JAM
    0.08
     ар
    0.07
     Sonoma
    0.07
     Drama
    0.07
    Act Density 0.421%

    No Known Activations