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

    Neuronpedia

    INDEX
    Explanations

    compound terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     아주
    0.40
     constaté
    0.40
    ocoder
    0.39
    जिन
    0.39
    低于
    0.39
    ்டர்
    0.39
    浐
    0.39
    झ्
    0.39
    低的
    0.39
    汨
    0.39
    POSITIVE LOGITS
     expect
    0.43
     দেখিয়া
    0.42
     robert
    0.41
     comes
    0.40
     technicians
    0.39
     hypothetical
    0.39
     belongs
    0.39
     Jays
    0.39
     constitutes
    0.39
     endeavour
    0.38
    Act Density 0.009%

    No Known Activations