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

    Neuronpedia

    INDEX
    Explanations

    SAT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     llam
    -0.07
     하지만
    -0.07
    .ef
    -0.06
     laughing
    -0.06
     betray
    -0.06
     rolling
    -0.06
    éments
    -0.06
    olute
    -0.06
    _r
    -0.06
     해
    -0.06
    POSITIVE LOGITS
    審
    0.07
    Sil
    0.06
    862
    0.06
     пес
    0.06
    (Context
    0.06
    findViewById
    0.06
    PURE
    0.06
     nem
    0.06
     BUS
    0.06
    ">'+↵
    0.06
    Act Density 0.005%

    No Known Activations