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

    Neuronpedia

    INDEX
    Explanations

    acquittal/verdict motions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \$
    -0.06
     Plans
    -0.06
     прав
    -0.06
     seconds
    -0.06
    リーズ
    -0.06
     接
    -0.06
    <<<<<<<
    -0.06
     맞
    -0.06
    Facade
    -0.06
    095
    -0.06
    POSITIVE LOGITS
     oggi
    0.08
    boys
    0.07
    wei
    0.07
    _CURSOR
    0.07
    'en
    0.07
     Oliver
    0.06
    explode
    0.06
    ционной
    0.06
    drop
    0.06
    كن
    0.06
    Act Density 0.005%

    No Known Activations