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

    Neuronpedia

    INDEX
    Explanations

    course

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    贞
    -0.07
     Juan
    -0.07
    -dist
    -0.07
     pineapple
    -0.07
     vig
    -0.07
     niezbę
    -0.07
    无形
    -0.07
    EA
    -0.06
     organs
    -0.06
    ていき
    -0.06
    POSITIVE LOGITS
    '],['
    0.07
     ←
    0.07
     ['
    0.07
    =['
    0.07
    可能是
    0.07
    )((((
    0.06
    .batch
    0.06
    ಅ
    0.06
    culture
    0.06
    雉
    0.06
    Act Density 0.005%

    No Known Activations