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

    Neuronpedia

    INDEX
    Explanations

    result

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     knot
    -0.08
    _street
    -0.07
    identifier
    -0.06
    datetime
    -0.06
     sunday
    -0.06
    ю
    -0.06
     khỏe
    -0.06
    ilies
    -0.06
     который
    -0.06
    fg
    -0.06
    POSITIVE LOGITS
    .reducer
    0.08
    (fc
    0.07
    ifen
    0.07
    -liter
    0.06
     rast
    0.06
     Пот
    0.06
     ماد
    0.06
     때문에
    0.06
    grim
    0.06
     sistemi
    0.06
    Act Density 0.009%

    No Known Activations