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

    Neuronpedia

    INDEX
    Explanations

    telegram bot api import

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rempl
    0.43
    ्याल
    0.39
    काशी
    0.39
     रोकने
    0.39
     ഏക
    0.39
    玮
    0.38
     रासायनिक
    0.38
     impotence
    0.38
    ecia
    0.38
     розгля
    0.38
    POSITIVE LOGITS
     "
    0.64
    "
    0.60
    _"
    0.57
     _
    0.48
    )"
    0.47
     “
    0.46
    ),"
    0.46
     _)
    0.46
    “
    0.46
     ."
    0.46
    Act Density 0.005%

    No Known Activations