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

    Neuronpedia

    INDEX
    Explanations

    sentence, move after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    0.78
    U
    0.75
    IN
    0.72
    น
    0.71
    د
    0.71
    യും
    0.69
     آ
    0.68
    י
    0.67
    จ
    0.67
    H
    0.66
    POSITIVE LOGITS
     glimpses
    0.76
    ,
    0.69
     contenders
    0.68
     savers
    0.68
     dampers
    0.66
     tendencies
    0.66
     rankings
    0.64
     pitfalls
    0.64
     casualties
    0.63
     quirks
    0.63
    Act Density 2.093%

    No Known Activations