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

    Neuronpedia

    INDEX
    Explanations

    Discourse Representation Structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     blatantly
    0.50
     croire
    0.46
     kredit
    0.46
     ""`
    0.46
     baffle
    0.44
     suspicions
    0.44
     ми
    0.43
     eigen
    0.43
     certainly
    0.43
     высо
    0.42
    POSITIVE LOGITS
    amd
    0.55
    必要があります
    0.51
    ‌ی
    0.49
    âmb
    0.48
    خدام
    0.48
    ьа
    0.47
    ложения
    0.46
    持续
    0.46
    orea
    0.45
    oze
    0.45
    Act Density 0.000%

    No Known Activations