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

    Neuronpedia

    INDEX
    Explanations

    recipe for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     otp
    0.44
    floxacin
    0.40
    महा
    0.40
    कामना
    0.39
    ammam
    0.39
    Benchmarks
    0.39
     kl
    0.39
    Oops
    0.39
    坚
    0.38
     seemed
    0.38
    POSITIVE LOGITS
     другого
    0.43
     ANOTHER
    0.43
     OTHER
    0.42
     другому
    0.40
    tras
    0.40
     laces
    0.40
     Cours
    0.39
     другое
    0.39
    ريس
    0.38
     இன்னொரு
    0.38
    Act Density 0.000%

    No Known Activations