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

    Neuronpedia

    INDEX
    Explanations

    UI tabs and elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    י
    0.22
    t
    0.21
    রকম
    0.20
    ுங்கள்
    0.19
    们的
    0.19
    tied
    0.19
    due
    0.19
    est
    0.19
    )$$
    0.19
    >\<
    0.18
    POSITIVE LOGITS
     limpi
    0.22
     sina
    0.21
     asin
    0.20
    ل
    0.20
     xanth
    0.20
     cyclohexane
    0.19
     micelles
    0.19
     Zum
    0.19
    ्रमण
    0.19
    ipynb
    0.19
    Act Density 0.333%

    No Known Activations