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

    Neuronpedia

    INDEX
    Explanations

    Puzzles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <<
    -0.07
     email
    -0.07
     read
    -0.07
     bluetooth
    -0.06
     {↵↵↵↵
    -0.06
     cognitive
    -0.06
    auction
    -0.06
     interesting
    -0.06
     responded
    -0.06
     shutdown
    -0.06
    POSITIVE LOGITS
    积
    0.07
    irate
    0.06
    積
    0.06
    ör
    0.06
    _sess
    0.06
    anganese
    0.06
     výše
    0.06
     electr
    0.06
     niệm
    0.06
    ‌باشد
    0.06
    Act Density 0.039%

    No Known Activations