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

    Neuronpedia

    INDEX
    Explanations

    Location

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Factory
    -0.07
    кт
    -0.07
    пис
    -0.06
     leve
    -0.06
     není
    -0.06
     dess
    -0.06
    regnum
    -0.06
    통령
    -0.06
     resolve
    -0.06
    *T
    -0.06
    POSITIVE LOGITS
     striking
    0.07
     =↵
    0.07
    tiler
    0.06
     είναι
    0.06
    ip
    0.06
     impressive
    0.06
     mAdapter
    0.06
     setSearch
    0.06
    ینگ
    0.06
     pics
    0.06
    Act Density 0.025%

    No Known Activations