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

    Neuronpedia

    INDEX
    Explanations

    citizenship

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dospěl
    -0.06
    ，因
    -0.06
    thumbnails
    -0.06
     جر
    -0.06
     quat
    -0.06
    르
    -0.06
    .language
    -0.06
    머니
    -0.06
    °F
    -0.06
    精神
    -0.05
    POSITIVE LOGITS
    (report
    0.08
     istediğiniz
    0.07
    _sr
    0.07
     sentir
    0.07
    (pic
    0.06
     vál
    0.06
     HOR
    0.06
    """)↵
    0.06
     toasted
    0.06
     Half
    0.06
    Act Density 0.078%

    No Known Activations