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

    Neuronpedia

    INDEX
    Explanations

    potentially followed by an outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ন
    1.52
    ో
    1.45
    ان
    1.40
    зва
    1.36
    ر
    1.33
    ında
    1.30
    ва
    1.30
    Smartphone
    1.27
    ன்
    1.25
    て
    1.22
    POSITIVE LOGITS
    ological
    1.16
    もっと
    1.08
    plot
    1.07
     extraordinaire
    1.07
    it
    1.03
     generates
    1.02
     pribadi
    1.01
    ;
    1.01
     authorizes
    0.98
     jedna
    0.97
    Act Density 0.276%

    No Known Activations