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

    Neuronpedia

    INDEX
    Explanations

    Google DeepMind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Obamacare
    0.57
     미리
    0.54
     swatch
    0.54
     Canva
    0.53
     toolbar
    0.52
     Bhagavato
    0.50
     FAQ
    0.49
     가
    0.48
     목록
    0.47
     countertop
    0.47
    POSITIVE LOGITS
    大学
    0.59
    கால
    0.58
    ᱑
    0.57
    கடந்த
    0.55
    ுக
    0.54
    இந்த
    0.54
     universitet
    0.54
    வில
    0.53
    并在
    0.53
    𝘮
    0.52
    Act Density 0.026%

    No Known Activations