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

    Neuronpedia

    INDEX
    Explanations

    jars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     getBitmap
    0.64
    льный
    0.59
     Yn
    0.59
    wedge
    0.58
     আঘাতে
    0.58
    arjo
    0.57
     Dön
    0.57
     Büh
    0.57
    printDialog
    0.56
     ಹೇಳಿದರು
    0.56
    POSITIVE LOGITS
     jars
    0.80
     vials
    0.75
     jar
    0.67
     rossa
    0.64
    v
    0.63
    Jar
    0.60
    imizi
    0.59
     bottles
    0.59
     lọ
    0.57
     names
    0.55
    Act Density 0.005%

    No Known Activations