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

    Neuronpedia

    INDEX
    Explanations

    tutorial requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    odio
    0.48
     krä
    0.48
     কূটনৈতিক
    0.46
     Geißler
    0.46
    <unused580>
    0.46
    ao
    0.45
     vä
    0.44
     Mastercard
    0.44
    oléon
    0.44
     Mario
    0.43
    POSITIVE LOGITS
    ى
    0.47
    체를
    0.46
    िंग
    0.44
    Mud
    0.41
    م
    0.41
    迫
    0.41
    regular
    0.40
    専用
    0.40
    pillars
    0.40
    ன
    0.40
    Act Density 0.006%

    No Known Activations