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

    Neuronpedia

    INDEX
    Explanations

    From

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ощ
    -0.07
     Ξ
    -0.07
    軟
    -0.07
    .findBy
    -0.07
     сред
    -0.06
    stein
    -0.06
     Zika
    -0.06
    _CTL
    -0.06
    اران
    -0.06
    _FINE
    -0.06
    POSITIVE LOGITS
     From
    0.08
     from
    0.07
     ()↵
    0.07
    From
    0.07
    ***/↵
    0.07
    ams
    0.07
    _)↵
    0.06
    ").↵↵
    0.06
    _diff
    0.06
     {}↵↵
    0.06
    Act Density 0.020%

    No Known Activations