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

    Neuronpedia

    INDEX
    Explanations

    replacement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    熏
    -0.06
    แอ
    -0.06
     Những
    -0.06
    Ind
    -0.06
     המת
    -0.06
    _motion
    -0.06
    -cor
    -0.06
    ऐ
    -0.06
    中有
    -0.06
    耐
    -0.06
    POSITIVE LOGITS
    难免
    0.08
     mechanism
    0.07
     rdr
    0.07
     paramName
    0.07
     demon
    0.07
    มาตรฐาน
    0.07
    yas
    0.07
     upgrade
    0.07
    https
    0.07
    _entry
    0.07
    Act Density 0.003%

    No Known Activations