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

    Neuronpedia

    INDEX
    Explanations

    [

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بازیگر
    -0.06
    anj
    -0.06
    orne
    -0.06
     PS
    -0.06
     Bitcoins
    -0.06
    raně
    -0.06
    Christopher
    -0.06
    reibung
    -0.06
     Ill
    -0.06
     myself
    -0.06
    POSITIVE LOGITS
    Cum
    0.08
     Cum
    0.07
     mic
    0.07
    uct
    0.07
    .erase
    0.07
    $return
    0.07
    *M
    0.07
    чив
    0.06
     여성
    0.06
    قط
    0.06
    Act Density 0.018%

    No Known Activations