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

    Neuronpedia

    INDEX
    Explanations

    language model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    苌
    0.45
    睑
    0.41
    šnje
    0.41
    muş
    0.40
     राग
    0.40
    issaient
    0.40
    larımız
    0.40
    印象
    0.39
     কাপড়
    0.38
     račun
    0.38
    POSITIVE LOGITS
     spoken
    0.89
     fluency
    0.82
     Processing
    0.76
     proficiency
    0.76
     processing
    0.71
     Proficiency
    0.71
     Flu
    0.67
     Barrier
    0.67
     barrier
    0.65
    processing
    0.62
    Act Density 0.063%

    No Known Activations