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

    Neuronpedia

    INDEX
    Explanations

    possible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     дом
    -0.07
    еди
    -0.07
     believable
    -0.06
     markets
    -0.06
     pup
    -0.06
    نم
    -0.06
     popul
    -0.06
    .feed
    -0.06
    _birth
    -0.06
    <pair
    -0.06
    POSITIVE LOGITS
    湾
    0.06
    ‰
    0.06
     や
    0.06
     **/
↵
    0.06
     mnoho
    0.06
    JB
    0.06
    ↵↵↵↵↵↵
    0.06
     bisher
    0.06
     Mosul
    0.06
    ῦ
    0.06
    Act Density 0.043%

    No Known Activations