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

    Neuronpedia

    INDEX
    Explanations

    appropriate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prelim
    -0.07
     centres
    -0.07
     ($("#
    -0.06
     %.
    -0.06
     movies
    -0.06
     winner
    -0.06
    582
    -0.06
    -Tr
    -0.06
     res
    -0.06
     Gym
    -0.06
    POSITIVE LOGITS
     appropriate
    0.13
     appropriately
    0.09
    appropriate
    0.09
     uygun
    0.07
     inappropriate
    0.07
    quired
    0.07
    śli
    0.07
    apat
    0.07
    fte
    0.07
    chap
    0.07
    Act Density 0.028%

    No Known Activations