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

    Neuronpedia

    INDEX
    Explanations

    rin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    улю
    -0.07
    lige
    -0.06
     Coul
    -0.06
     подроб
    -0.06
    ancock
    -0.06
    aryana
    -0.06
    notice
    -0.06
    ijing
    -0.06
     tướng
    -0.06
     Rahman
    -0.06
    POSITIVE LOGITS
    Languages
    0.07
    :class
    0.06
     Args
    0.06
     mat
    0.06
     disciplined
    0.06
     の
    0.06
    ,true
    0.06
     ly
    0.06
     bubbles
    0.06
    _native
    0.06
    Act Density 0.003%

    No Known Activations