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

    Neuronpedia

    INDEX
    Explanations

    dirty talk, raw fish, being called

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tôi
    0.66
    ප
    0.64
     তারই
    0.62
    １
    0.61
     Νο
    0.61
     בי
    0.61
     setInterval
    0.61
    setInterval
    0.58
    网址
    0.58
    走了
    0.56
    POSITIVE LOGITS
     update
    0.49
    듈
    0.49
    糬
    0.48
    udu
    0.48
     непосредственно
    0.45
    uben
    0.44
    olytic
    0.44
     hogy
    0.44
     warriors
    0.44
    兮
    0.44
    Act Density 0.000%

    No Known Activations