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
    Pokemon
    -0.07
     Circular
    -0.06
    ература
    -0.06
     Syn
    -0.06
    ">'.$
    -0.06
    (instance
    -0.06
    elon
    -0.06
     SUBSTITUTE
    -0.06
    (Contact
    -0.06
     面
    -0.06
    POSITIVE LOGITS
    Ñ
    0.06
    웠
    0.06
    SURE
    0.06
     běž
    0.06
    inea
    0.06
    žit
    0.06
    مدة
    0.06
    ažd
    0.06
    еристи
    0.06
    ledik
    0.06
    Act Density 0.000%

    No Known Activations