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

    Neuronpedia

    INDEX
    Explanations

    art

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    powers
    -0.06
     Her
    -0.06
     her
    -0.06
     Mend
    -0.06
    ViewPager
    -0.06
     tokens
    -0.06
     sek
    -0.06
     Blackhawks
    -0.06
    ies
    -0.06
     amateurs
    -0.06
    POSITIVE LOGITS
     득
    0.07
     Địa
    0.07
    .cent
    0.07
    ToWorld
    0.07
    ={<
    0.07
    �
    0.06
    .instagram
    0.06
    -positive
    0.06
    +W
    0.06
    _component
    0.06
    Act Density 0.016%

    No Known Activations