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

    Neuronpedia

    INDEX
    Explanations

    scientific/medical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     以
    -0.07
    據
    -0.07
    рь
    -0.06
    τιν
    -0.06
     EACH
    -0.06
    menin
    -0.06
     таком
    -0.06
     этим
    -0.06
     lock
    -0.06
     जम
    -0.06
    POSITIVE LOGITS
    Nama
    0.07
    Clearly
    0.07
     nil
    0.07
     COMMON
    0.06
    anggal
    0.06
     skateboard
    0.06
     cheesy
    0.06
    .links
    0.06
    .delivery
    0.06
    .setState
    0.06
    Act Density 0.262%

    No Known Activations