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

    Neuronpedia

    INDEX
    Explanations

    Use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ned
    -0.07
    indexPath
    -0.07
     vou
    -0.07
     Stmt
    -0.07
    营业
    -0.07
    wav
    -0.07
     amen
    -0.07
     nth
    -0.07
    Vect
    -0.07
     Zombies
    -0.07
    POSITIVE LOGITS
     tướng
    0.08
    -centric
    0.07
    $s
    0.07
    -item
    0.07
    ﭽ
    0.07
     그러나
    0.07
    רים
    0.06
    虷
    0.06
    -cart
    0.06
     Pure
    0.06
    Act Density 0.014%

    No Known Activations