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

    Neuronpedia

    INDEX
    Explanations

    */

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     skills
    -0.07
    �
    -0.07
     jj
    -0.07
    keyup
    -0.07
    tele
    -0.07
    (kind
    -0.06
    =?
    -0.06
     степ
    -0.06
    _mar
    -0.06
    ^-
    -0.06
    POSITIVE LOGITS
     LEDs
    0.07
     processors
    0.07
     ArrayList
    0.07
     Presbyterian
    0.07
    arms
    0.07
    野生动物
    0.06
     Graph
    0.06
    :');↵
    0.06
    نظ
    0.06
    urat
    0.06
    Act Density 0.001%

    No Known Activations