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

    Neuronpedia

    INDEX
    Explanations

    single quotes and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ázal
    -0.07
    vens
    -0.07
    ्रय
    -0.06
    PRS
    -0.06
    яд
    -0.06
     Airways
    -0.06
    šší
    -0.06
     stiff
    -0.06
     RH
    -0.06
    ill
    -0.06
    POSITIVE LOGITS
    _DD
    0.06
     지정
    0.06
     wd
    0.06
    (Qt
    0.06
    ản
    0.06
     определить
    0.06
    (!
    0.06
     �
    0.06
    它
    0.06
    (t
    0.06
    Act Density 0.000%

    No Known Activations