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

    Neuronpedia

    INDEX
    Explanations

    Korean character

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grazing
    -0.08
     cata
    -0.07
    mada
    -0.07
    &page
    -0.07
     agar
    -0.07
    ється
    -0.07
    jam
    -0.07
    .callback
    -0.07
     chu
    -0.07
    .member
    -0.06
    POSITIVE LOGITS
    uč
    0.07
    uddenly
    0.06
    “Well
    0.06
     Advoc
    0.06
    amazon
    0.06
    Й
    0.06
    "Yes
    0.06
     NEW
    0.06
     Сим
    0.06
     베스트
    0.06
    Act Density 0.001%

    No Known Activations