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

    Neuronpedia

    INDEX
    Explanations

    thrust

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hình
    -0.07
    録
    -0.07
    ény
    -0.06
    ござ
    -0.06
     Personen
    -0.06
     продаж
    -0.06
    attice
    -0.06
    ая
    -0.06
    Foo
    -0.06
     Peggy
    -0.06
    POSITIVE LOGITS
     thrust
    0.14
     flushed
    0.07
     Thr
    0.07
     lift
    0.06
    queeze
    0.06
    scatter
    0.06
    /win
    0.06
    轉
    0.06
     Wishlist
    0.06
    Represent
    0.06
    Act Density 0.001%

    No Known Activations