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

    Neuronpedia

    INDEX
    Explanations

    Loss or gain of control

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     erh
    -0.06
    领
    -0.06
     těch
    -0.06
     Mou
    -0.06
    <Comment
    -0.06
    (record
    -0.06
    aad
    -0.06
     přičemž
    -0.06
     ukon
    -0.06
    mî
    -0.06
    POSITIVE LOGITS
    onomic
    0.07
    檢
    0.07
    ΑΓ
    0.06
     VARCHAR
    0.06
     telecommunications
    0.06
    !)
    0.06
     Gig
    0.06
    istique
    0.06
    自動
    0.06
    WP
    0.06
    Act Density 0.184%

    No Known Activations