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

    Neuronpedia

    INDEX
    Explanations

    accurately

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rng
    -0.07
     heed
    -0.07
    _rates
    -0.07
    iesz
    -0.07
     בשנים
    -0.06
     enjo
    -0.06
    '].$
    -0.06
    WASHINGTON
    -0.06
    牵手
    -0.06
    Wie
    -0.06
    POSITIVE LOGITS
    Об
    0.07
     analyse
    0.07
     eigentlich
    0.07
     Ask
    0.07
     “
    0.07
    봇
    0.07
     Returned
    0.07
     באמת
    0.06
    alcon
    0.06
    Ք
    0.06
    Act Density 0.021%

    No Known Activations