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

    Neuronpedia

    INDEX
    Explanations

    foot, footnote, footer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Silent
    0.43
     silent
    0.41
     grinding
    0.41
     wading
    0.39
     Adder
    0.39
     Orrell
    0.38
     Broken
    0.38
     थ
    0.38
     wade
    0.38
     Conversation
    0.38
    POSITIVE LOGITS
    notes
    0.43
    note
    0.42
     પોતાની
    0.41
    CallBack
    0.41
     notes
    0.40
     notas
    0.40
     NOTES
    0.40
    NOTES
    0.39
     ся
    0.39
     نوٹ
    0.39
    Act Density 0.001%

    No Known Activations