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

    Neuronpedia

    INDEX
    Explanations

    native english speakers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     రూప
    0.52
    Fruit
    0.52
    ER
    0.50
    er
    0.49
    amente
    0.48
    EI
    0.48
    ct
    0.48
    IT
    0.48
    বৃত্তি
    0.47
    ò
    0.47
    POSITIVE LOGITS
     professional
    0.56
     whine
    0.55
     mechanic
    0.55
     kink
    0.55
     onboarding
    0.54
     oon
    0.53
     driveway
    0.52
    專業
    0.52
     elektro
    0.52
     whitelist
    0.52
    Act Density 0.004%

    No Known Activations