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

    Neuronpedia

    INDEX
    Explanations

    4

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hypertext
    0.40
     audiovis
    0.38
     discursive
    0.38
     nonfiction
    0.37
     sculptural
    0.36
     objekt
    0.35
     embroidery
    0.35
     motto
    0.35
     calligraphy
    0.35
     analges
    0.35
    POSITIVE LOGITS
    9
    0.52
    7
    0.50
    8
    0.46
    6
    0.43
    5
    0.42
    4
    0.42
    3
    0.41
    1
    0.39
    L
    0.37
    2
    0.36
    Act Density 0.004%

    No Known Activations