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

    Neuronpedia

    INDEX
    Explanations

    r

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    357
    -0.07
    ULL
    -0.07
    pattern
    -0.07
    meni
    -0.07
    ump
    -0.06
    ky
    -0.06
    ูต
    -0.06
     abortion
    -0.06
     cultures
    -0.06
    .J
    -0.06
    POSITIVE LOGITS
     середови
    0.07
     chick
    0.07
    _FETCH
    0.07
     جلس
    0.07
     redefine
    0.06
    站在
    0.06
     yönelik
    0.06
    [axis
    0.06
    (mapped
    0.06
    _lambda
    0.06
    Act Density 0.001%

    No Known Activations