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

    Neuronpedia

    INDEX
    Explanations

    detail

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kê
    -0.07
     shifted
    -0.07
    ick
    -0.06
    -the
    -0.06
     chất
    -0.06
    AH
    -0.06
    rah
    -0.06
    -ish
    -0.06
    كور
    -0.06
     ≥
    -0.06
    POSITIVE LOGITS
    ?)↵↵
    0.06
    andal
    0.06
    oglobin
    0.06
     spirituality
    0.06
    ожд
    0.06
     generously
    0.06
    ordinates
    0.06
    гу
    0.06
    lis
    0.06
    icester
    0.06
    Act Density 0.003%

    No Known Activations