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

    Neuronpedia

    INDEX
    Explanations

    Research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    맹
    -0.07
    ience
    -0.06
    มอ
    -0.06
    _bio
    -0.06
    �
    -0.06
    jej
    -0.06
    ोस
    -0.06
     hữu
    -0.06
    -design
    -0.06
    ινη
    -0.06
    POSITIVE LOGITS
     queryString
    0.06
    ."+
    0.06
    씀
    0.06
    =t
    0.06
    办理
    0.06
     شدن
    0.06
     staffing
    0.06
    operator
    0.06
     grat
    0.06
     війсь
    0.06
    Act Density 0.045%

    No Known Activations