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

    Neuronpedia

    INDEX
    Explanations

    pollution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (tc
    -0.07
     Gets
    -0.07
    إن
    -0.07
     compte
    -0.06
     environments
    -0.06
     pn
    -0.06
    Brand
    -0.06
     ke
    -0.06
    �
    -0.06
     Beer
    -0.06
    POSITIVE LOGITS
     из
    0.07
    ocation
    0.06
    locking
    0.06
    ]=[
    0.06
    acebook
    0.06
    specified
    0.06
    INCLUDING
    0.06
     nový
    0.06
     معماری
    0.06
    uky
    0.06
    Act Density 0.025%

    No Known Activations