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

    Neuronpedia

    INDEX
    Explanations

    param

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (uid
    -0.06
     zaman
    -0.06
    yní
    -0.06
    Login
    -0.06
    asia
    -0.06
    otts
    -0.06
     bundan
    -0.06
     sistem
    -0.06
    HIGH
    -0.06
     endeavor
    -0.06
    POSITIVE LOGITS
     continents
    0.07
     Cap
    0.06
    นส
    0.06
     attach
    0.06
    pert
    0.06
     siêu
    0.06
     Fires
    0.06
     fires
    0.06
    months
    0.06
    妮
    0.06
    Act Density 0.002%

    No Known Activations