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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    URIComponent
    -0.07
     uncovered
    -0.06
     návště
    -0.06
    007
    -0.06
    男
    -0.06
    言葉
    -0.06
    Today
    -0.06
     Boyd
    -0.06
    できる
    -0.06
    alles
    -0.06
    POSITIVE LOGITS
    )((
    0.07
    ([(
    0.06
    ('').
    0.06
    اهرة
    0.06
    toggleClass
    0.06
    heart
    0.06
    stin
    0.06
    ",$
    0.06
    urgence
    0.06
    かに
    0.06
    Act Density 0.004%

    No Known Activations