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

    Neuronpedia

    INDEX
    Explanations

    Stem Export

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     {"
    0.42
     {_
    0.40
     సన్ని
    0.39
    льм
    0.39
     (!
    0.38
     {{\
    0.38
    ភាព
    0.38
     (<
    0.38
     활용
    0.38
     (’
    0.37
    POSITIVE LOGITS
    affle
    0.42
    acja
    0.41
    ieve
    0.41
    定的
    0.40
     আরেকটি
    0.39
    engen
    0.37
    kr
    0.37
     vorgesehen
    0.37
    Quel
    0.37
     onClose
    0.37
    Act Density 0.000%

    No Known Activations