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

    Neuronpedia

    INDEX
    Explanations

    statistical analysis and prediction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     praktisch
    0.61
     Einwilligung
    0.61
     Einwill
    0.61
    िशनर
    0.60
    inky
    0.58
     tangy
    0.57
     duk
    0.57
     توضیح
    0.57
    lashes
    0.56
     melindungi
    0.56
    POSITIVE LOGITS
     statistical
    1.43
     Statistical
    1.18
    statistical
    1.17
     mathematical
    1.14
     algorithms
    1.12
    Statistical
    1.10
     Bayesian
    1.10
     econometric
    1.08
    机器学习
    1.05
     automated
    1.04
    Act Density 1.101%

    No Known Activations