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

    Neuronpedia

    INDEX
    Explanations

    Here's a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jeff
    0.49
    Jeff
    0.47
     mah
    0.43
    Jefferson
    0.43
    Flare
    0.41
     jeff
    0.40
     Jefferson
    0.40
     Mathieu
    0.39
     VISA
    0.39
    जफ्
    0.39
    POSITIVE LOGITS
     발
    0.38
    rtc
    0.37
    韵
    0.35
    뮤
    0.34
    gae
    0.34
    dac
    0.34
    堂
    0.33
    бор
    0.33
     проде
    0.33
    DO
    0.32
    Act Density 0.102%

    No Known Activations