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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Supported
    -0.07
    만남
    -0.07
     grave
    -0.07
     cotton
    -0.07
    673
    -0.06
     highway
    -0.06
    history
    -0.06
    uncio
    -0.06
    До
    -0.06
     diet
    -0.06
    POSITIVE LOGITS
    /'.
    0.06
    /tinyos
    0.06
    ｯ
    0.06
    arez
    0.06
    _META
    0.06
    .getOwnPropertyDescriptor
    0.06
     exploiting
    0.06
    정
    0.06
    '}
    0.06
     الفر
    0.05
    Act Density 0.108%

    No Known Activations