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

    Neuronpedia

    INDEX
    Explanations

    connection status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    如果是
    0.40
     limitations
    0.39
     grapple
    0.39
    にあ
    0.38
    Limitations
    0.38
     sním
    0.37
    চনার
    0.37
     गहराई
    0.37
    ibe
    0.35
     deepen
    0.35
    POSITIVE LOGITS
    anonymous
    0.39
    astronaut
    0.38
     util
    0.37
    ელს
    0.37
     irresponsible
    0.37
     pr
    0.36
    優秀
    0.36
    गेड
    0.36
     Clínica
    0.36
    शासित
    0.36
    Act Density 0.000%

    No Known Activations