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

    Neuronpedia

    INDEX
    Explanations

    problem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UCS
    -0.07
     recap
    -0.07
     /*
    -0.07
     matched
    -0.07
     المع
    -0.07
    ACC
    -0.06
    _cos
    -0.06
     streaming
    -0.06
     defenseman
    -0.06
     CharSequence
    -0.06
    POSITIVE LOGITS
     Written
    0.07
    (self
    0.07
    !!!!
    0.06
     pracovní
    0.06
     bla
    0.06
    RX
    0.06
    BTN
    0.06
     dva
    0.06
    関係
    0.06
    дрес
    0.06
    Act Density 0.024%

    No Known Activations