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

    Neuronpedia

    INDEX
    Explanations

    as well as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Overnight
    0.69
    track
    0.68
    Plain
    0.68
    ্ঠ
    0.68
    abyte
    0.66
    orneys
    0.66
    द्योगिक
    0.66
    siblings
    0.66
    χαν
    0.65
     הפ
    0.65
    POSITIVE LOGITS
     Lila
    0.72
    FLE
    0.72
    0.70
     ಜನ
    0.69
     ost
    0.68
     पुष्
    0.68
    adil
    0.67
     伊
    0.67
     obst
    0.66
    ”:
    0.66
    Act Density 0.000%

    No Known Activations