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

    Neuronpedia

    INDEX
    Explanations

    company experience or job titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    そして
    0.74
    क्षेप
    0.71
    그리고
    0.70
    வ்வாற
    0.69
     namespaces
    0.68
    parametri
    0.66
    polyfills
    0.65
    することで
    0.64
    များနှင့်
    0.64
    それ
    0.64
    POSITIVE LOGITS
     |
    1.20
     ১
    1.01
     February
    0.95
     January
    0.93
     ৯
    0.88
     \|
    0.88
     ৬
    0.88
     Feb
    0.86
     July
    0.85
     November
    0.85
    Act Density 0.000%

    No Known Activations