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

    Neuronpedia

    INDEX
    Explanations

    uncertainty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fault
    -0.07
    _RB
    -0.07
     DF
    -0.07
     вообще
    -0.07
    (('
    -0.06
     Viol
    -0.06
    ене
    -0.06
     {?
    -0.06
    алеж
    -0.06
    unicode
    -0.06
    POSITIVE LOGITS
     Enjoy
    0.06
    Copying
    0.06
    해야
    0.06
    _cb
    0.06
     doprov
    0.06
     mut
    0.06
     Heller
    0.06
    {},↵
    0.06
     ε�
    0.06
     вкус
    0.06
    Act Density 0.023%

    No Known Activations