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

    Neuronpedia

    INDEX
    Explanations

    safe environment and space

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    0.71
    s
    0.58
     don
    0.57
     čís
    0.55
     expenditures
    0.54
    យ៉
    0.54
     τέ
    0.53
     quente
    0.52
     lengthened
    0.52
     endere
    0.52
    POSITIVE LOGITS
    жок
    0.60
    氛围
    0.58
    雰囲気
    0.57
    зін
    0.57
    щик
    0.56
    šina
    0.52
    지로
    0.50
    сіб
    0.49
    вара
    0.49
    логи
    0.49
    Act Density 0.056%

    No Known Activations