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

    Neuronpedia

    INDEX
    Explanations

    USDA loan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    re
    0.96
    jax
    0.91
    ナ
    0.85
    他人
    0.85
    Fry
    0.84
    Spring
    0.83
    いますが
    0.83
     heather
    0.82
     whor
    0.81
    Heather
    0.81
    POSITIVE LOGITS
     inaugurated
    1.17
     reportedly
    1.13
     правильно
    1.09
     chỉ
    1.07
    клады
    1.04
     devait
    1.04
    कुल
    1.02
     وكانت
    1.01
     interpol
    1.01
     receivables
    0.99
    Act Density 0.001%

    No Known Activations