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

    Neuronpedia

    INDEX
    Explanations

    code keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iterable
    0.85
    adrat
    0.84
     dago
    0.83
    াভাবিক
    0.82
     aproximativ
    0.82
    汥
    0.81
    neet
    0.81
    ﻠ
    0.80
    phalodes
    0.80
    unarod
    0.80
    POSITIVE LOGITS
    ต่างๆ
    0.73
     layering
    0.70
     Setup
    0.69
     통한
    0.69
    များ
    0.69
     Reliance
    0.69
     setup
    0.68
     setups
    0.68
     הרב
    0.67
     لگانا
    0.67
    Act Density 0.147%

    No Known Activations