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

    Neuronpedia

    INDEX
    Explanations

    actionable suggestions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝘬
    0.42
     codified
    0.40
     choosing
    0.38
    佸
    0.38
     సే
    0.37
    મે
    0.37
     \%\
    0.37
     NONCLUSTERED
    0.36
    وام
    0.36
     comical
    0.36
    POSITIVE LOGITS
    жных
    0.40
    arier
    0.39
    ulaire
    0.38
     تنها
    0.38
    更高
    0.38
    ilaian
    0.38
     busier
    0.37
    csak
    0.37
     growths
    0.37
    Refs
    0.36
    Act Density 0.000%

    No Known Activations