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

    Neuronpedia

    INDEX
    Explanations

    hypnosis and suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    一个人
    -0.06
    樓
    -0.06
    uropean
    -0.06
    続
    -0.06
    coholic
    -0.06
    _LIMIT
    -0.06
     senior
    -0.06
    ことを
    -0.06
     gpio
    -0.06
    iect
    -0.06
    POSITIVE LOGITS
    休
    0.07
    Bins
    0.07
    (UnmanagedType
    0.06
    measurement
    0.06
    Aaron
    0.06
    返
    0.06
    881
    0.06
     Camb
    0.06
    akers
    0.06
    _att
    0.06
    Act Density 0.001%

    No Known Activations