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

    Neuronpedia

    INDEX
    Explanations

    python import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     omitting
    0.54
     nonexistent
    0.54
     omit
    0.50
     unambiguously
    0.49
     discredited
    0.47
     omitted
    0.47
     diodes
    0.47
     reconsider
    0.46
     superseded
    0.46
     disassembled
    0.46
    POSITIVE LOGITS
    م
    0.58
    #
    0.54
    आज
    0.54
    Sentiment
    0.49
    আজ
    0.48
    Programme
    0.47
    import
    0.46
    All
    0.45
    m
    0.45
    ir
    0.44
    Act Density 0.005%

    No Known Activations