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

    Neuronpedia

    INDEX
    Explanations

    before

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Schweizer
    -0.09
     relieve
    -0.08
     imobili
    -0.08
    Prelude
    -0.08
     relieving
    -0.07
    netic
    -0.07
     subconscious
    -0.07
     assigns
    -0.07
    reb
    -0.07
    estate
    -0.07
    POSITIVE LOGITS
     Veranst
    0.09
     substantially
    0.09
    左右
    0.08
     Meal
    0.08
     ഡ്ര
    0.08
     معظم
    0.08
    授权
    0.08
     Absatz
    0.08
     maamulka
    0.08
    ാസ
    0.08
    Act Density 0.013%

    No Known Activations