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

    Neuronpedia

    INDEX
    Explanations

    easily

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hait
    -0.06
     Dez
    -0.06
    stud
    -0.06
     tvrd
    -0.06
     naopak
    -0.06
     Gov
    -0.06
    Mat
    -0.06
    tea
    -0.06
     Лю
    -0.06
     summarized
    -0.06
    POSITIVE LOGITS
    )=
    0.07
    ILED
    0.06
    '),'
    0.06
    ouncement
    0.06
    '><
    0.06
    .sm
    0.06
    ↵		
↵
    0.06
    рг
    0.06
     mata
    0.06
    _PATH
    0.06
    Act Density 0.047%

    No Known Activations