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

    Neuronpedia

    INDEX
    Explanations

    return policies and shipping

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Release
    -0.08
     Intellectual
    -0.07
     Coupons
    -0.07
     cell
    -0.07
     nghệ
    -0.07
     firm
    -0.06
     guardar
    -0.06
     avocado
    -0.06
     Cell
    -0.06
    Term
    -0.06
    POSITIVE LOGITS
    <dd
    0.07
     homicides
    0.06
    müş
    0.06
     undesirable
    0.06
     recycle
    0.06
    に入
    0.06
     민
    0.06
     aşağı
    0.06
     "<<
    0.06
    _IRQ
    0.06
    Act Density 0.022%

    No Known Activations