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

    Neuronpedia

    INDEX
    Explanations

    linking descriptor to subject

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    м
    0.69
    ي
    0.65
    م
    0.59
    י
    0.56
     Conan
    0.52
    ك
    0.52
    ت
    0.50
    ن
    0.49
    ி
    0.49
    त
    0.48
    POSITIVE LOGITS
     범위
    0.46
     boar
    0.45
    லி
    0.45
     wildly
    0.45
    ithub
    0.44
    ിക്കാം
    0.44
    NS
    0.42
     தருக
    0.42
    ಷ್ಣ
    0.42
     탁
    0.42
    Act Density 0.000%

    No Known Activations