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

    Neuronpedia

    INDEX
    Explanations

    `argparse.ArgumentParser` descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     soluciones
    0.42
    䋇
    0.39
     recom
    0.39
    calup
    0.39
     ORIGINAL
    0.38
     हिल
    0.38
    DeathRecord
    0.38
     energías
    0.38
    飨
    0.37
     prácticas
    0.37
    POSITIVE LOGITS
    oye
    0.39
     kend
    0.38
     ken
    0.38
    शिला
    0.38
    indows
    0.37
     Assignment
    0.37
     opa
    0.37
     Sh
    0.37
     Engineers
    0.37
    pozn
    0.36
    Act Density 0.000%

    No Known Activations