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

    Neuronpedia

    INDEX
    Explanations

    generating unpredictable keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    রায়
    0.40
    Ბ
    0.40
     wickedness
    0.40
    NESOTA
    0.38
    ONEDB
    0.38
     hepatic
    0.38
     richesse
    0.38
     FUNDS
    0.38
     honoring
    0.37
    }~
    0.37
    POSITIVE LOGITS
    Find
    0.70
    Related
    0.64
    Subscribe
    0.60
     Find
    0.59
    Popular
    0.59
    What
    0.58
    Ad
    0.57
    find
    0.57
    See
    0.57
    Disclaimer
    0.57
    Act Density 0.000%

    No Known Activations