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

    Neuronpedia

    INDEX
    Explanations

    file names (csv)

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lan
    0.60
     interpretive
    0.57
     perceptive
    0.56
    MORE
    0.55
     idealism
    0.54
    REAT
    0.53
     Psy
    0.53
     Meinung
    0.53
     Cold
    0.52
     Justicia
    0.52
    POSITIVE LOGITS
     csv
    1.23
     filenames
    1.22
    csv
    1.16
     filename
    1.13
    filenames
    1.05
     файла
    1.05
    filename
    1.04
     CSV
    1.04
     filepath
    1.01
    CSV
    1.01
    Act Density 0.323%

    No Known Activations