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

    Neuronpedia

    INDEX
    Explanations

    introducing numbered sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    1.27
    2
    1.16
    ۱
    1.03
    5
    0.99
    3
    0.96
    7
    0.95
     parser
    0.91
    6
    0.90
    A
    0.89
    ১
    0.88
    POSITIVE LOGITS
     empowering
    0.76
     Training
    0.73
     Website
    0.72
     चै
    0.72
     Direct
    0.71
     Environmental
    0.71
     Breakdown
    0.71
     Evangel
    0.70
     actual
    0.69
     Pay
    0.69
    Act Density 0.102%

    No Known Activations