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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     amino
    -0.08
    坦言
    -0.07
    iena
    -0.07
    chk
    -0.07
    Clicked
    -0.07
    明确了
    -0.07
    ascus
    -0.07
    "]["
    -0.07
    _payload
    -0.07
     cheaper
    -0.07
    POSITIVE LOGITS
    .omg
    0.07
     באו
    0.07
     Jeżeli
    0.07
     vários
    0.07
    (dist
    0.06
    꼴
    0.06
    :absolute
    0.06
    鸽
    0.06
    딴
    0.06
    RIES
    0.06
    Act Density 0.057%

    No Known Activations