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

    Neuronpedia

    INDEX
    Explanations

    urls and articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Probab
    0.73
    Radar
    0.71
    狯
    0.71
    NMR
    0.71
    ravariant
    0.70
     ervoor
    0.70
     बातम्या
    0.69
    หัว
    0.69
    nbhost
    0.69
     খোঁজ
    0.69
    POSITIVE LOGITS
     (
    0.65
    处
    0.63
     మంత్రి
    0.63
    性の
    0.62
     gül
    0.60
     ato
    0.59
     sop
    0.59
     （
    0.58
     (‘
    0.58
     vaj
    0.58
    Act Density 0.030%

    No Known Activations