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

    Neuronpedia

    INDEX
    Explanations

    upon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “So
    -0.08
    lossen
    -0.07
     retention
    -0.07
    %;↵
    -0.07
    ร
    -0.07
     revenge
    -0.07
     Nutrition
    -0.07
    Ленин
    -0.07
    zzarella
    -0.07
     Nolan
    -0.07
    POSITIVE LOGITS
     the
    0.09
     upon
    0.09
    变压
    0.07
     стали
    0.07
     כמה
    0.07
     hàng
    0.07
    placed
    0.06
     commun
    0.06
    (vector
    0.06
     troublesome
    0.06
    Act Density 0.020%

    No Known Activations