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

    Neuronpedia

    INDEX
    Explanations

    language variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eter
    0.78
    io
    0.75
    ing
    0.74
    תן
    0.73
    angular
    0.72
    ali
    0.70
     popolo
    0.70
    ８
    0.70
    Bot
    0.69
    Social
    0.69
    POSITIVE LOGITS
     электрон
    0.78
    ленность
    0.74
     п
    0.73
     лест
    0.71
     shortlist
    0.71
     therapeut
    0.68
     специа
    0.68
     multiv
    0.66
     buscador
    0.66
     इतना
    0.66
    Act Density 0.001%

    No Known Activations