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

    Neuronpedia

    INDEX
    Explanations

    code elements followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Intensive
    0.87
     ;,
    0.81
     رکھیں
    0.77
     Virtual
    0.77
     UserDefaults
    0.77
     ;$
    0.75
     "|"
    0.74
     Leaving
    0.73
     Fulfillment
    0.72
    Issledovatel
    0.71
    POSITIVE LOGITS
    .
    2.28
    _.
    1.81
    *.
    1.74
    -.
    1.61
    __.
    1.59
    ().
    1.57
    ._
    1.52
    .\
    1.48
     .
    1.47
    .(
    1.45
    Act Density 0.183%

    No Known Activations