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

    Neuronpedia

    INDEX
    Explanations

    pec

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    common
    -0.07
    忠
    -0.07
    "After
    -0.06
    _door
    -0.06
    �
    -0.06
    Sha
    -0.06
     appId
    -0.06
     svět
    -0.06
     Chúa
    -0.06
    .DATA
    -0.06
    POSITIVE LOGITS
    �
    0.07
     etmek
    0.07
     happy
    0.06
     ông
    0.06
     lasts
    0.06
     chancellor
    0.06
     пла
    0.06
    zem
    0.06
    LookAndFeel
    0.06
     Hosp
    0.06
    Act Density 0.001%

    No Known Activations