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

    Neuronpedia

    INDEX
    Explanations

    magnet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     خاصة
    -0.07
     توص
    -0.07
     немає
    -0.06
    (est
    -0.06
    Latitude
    -0.06
    153
    -0.06
    Esc
    -0.06
    checker
    -0.06
     الدر
    -0.06
    بدأ
    -0.06
    POSITIVE LOGITS
     instruct
    0.07
    .magnitude
    0.07
     양
    0.06
     premature
    0.06
    tering
    0.06
     literary
    0.06
    -items
    0.06
    angstrom
    0.06
    .activate
    0.06
    reeting
    0.06
    Act Density 0.001%

    No Known Activations