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

    Neuronpedia

    INDEX
    Explanations

    spectrum

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    腰
    -0.07
     delet
    -0.06
     norm
    -0.06
     ارز
    -0.06
    ालन
    -0.06
     resistance
    -0.06
    精神
    -0.06
    .f
    -0.06
    -rel
    -0.06
    乾
    -0.06
    POSITIVE LOGITS
     Medal
    0.07
     сов
    0.07
    _dictionary
    0.07
    .SK
    0.07
    دم
    0.06
    idon
    0.06
     днів
    0.06
    (dialog
    0.06
     spectra
    0.06
    Inserted
    0.06
    Act Density 0.008%

    No Known Activations