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

    Neuronpedia

    INDEX
    Explanations

    module paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     సమ
    0.42
     aparece
    0.41
     Vietnamese
    0.40
     якого
    0.40
     cukup
    0.39
     pages
    0.39
     EtOH
    0.39
     punched
    0.38
     Rapid
    0.38
     Tutak
    0.38
    POSITIVE LOGITS
    types
    0.68
    interfaces
    0.67
     types
    0.59
    typ
    0.52
    }}$;
    0.47
     interfaces
    0.47
     dist
    0.46
     типов
    0.45
     tipos
    0.45
     util
    0.45
    Act Density 0.006%

    No Known Activations