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

    Neuronpedia

    INDEX
    Explanations

    information on labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अड
    0.42
    літы
    0.42
    ራም
    0.41
    onnés
    0.40
    Document
    0.39
     Document
    0.39
    Sessions
    0.39
    撷
    0.38
     Refs
    0.37
     ഹിന്ദു
    0.37
    POSITIVE LOGITS
     labels
    1.45
     label
    1.36
     labeling
    1.36
     labelling
    1.33
     Labels
    1.23
    labels
    1.16
     Label
    1.16
    label
    1.13
    Label
    1.10
     LABEL
    1.10
    Act Density 0.016%

    No Known Activations