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

    Neuronpedia

    INDEX
    Explanations

    (n

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Urlaub
    -0.08
     Catalunya
    -0.07
    geving
    -0.07
    偷偷
    -0.07
     Derr
    -0.07
     Keeping
    -0.07
     España
    -0.07
     оформить
    -0.07
     Senhora
    -0.07
    ственное
    -0.07
    POSITIVE LOGITS
     सत्य
    0.08
     melee
    0.08
     mob
    0.08
    艳
    0.07
     AFL
    0.07
     passions
    0.07
     aventure
    0.07
    ferm
    0.07
    -ri
    0.07
     सोन
    0.07
    Act Density 0.009%

    No Known Activations