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

    Neuronpedia

    INDEX
    Explanations

    News/blog excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pretty
    -0.07
     Expedition
    -0.06
    simple
    -0.06
    νο
    -0.06
    ент
    -0.06
    _save
    -0.06
    _xy
    -0.06
    伏
    -0.06
     sắc
    -0.06
     phẩm
    -0.06
    POSITIVE LOGITS
    npj
    0.07
    하지
    0.07
     grad
    0.07
     danske
    0.06
     GlobalKey
    0.06
    umont
    0.06
    Grad
    0.06
    rors
    0.06
     Rating
    0.06
     роки
    0.06
    Act Density 0.224%

    No Known Activations