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

    Neuronpedia

    INDEX
    Explanations

    business/website mentions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     domin
    -0.07
     bricks
    -0.07
    Flow
    -0.07
     bg
    -0.07
     parents
    -0.06
     seemingly
    -0.06
     totally
    -0.06
     BroadcastReceiver
    -0.06
     корп
    -0.06
    Being
    -0.06
    POSITIVE LOGITS
    ruh
    0.08
    .poll
    0.07
    HT
    0.06
    ｯ
    0.06
    üyoruz
    0.06
    pirit
    0.06
     gle
    0.06
     quarter
    0.06
    (blob
    0.06
    alary
    0.06
    Act Density 0.066%

    No Known Activations