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

    Neuronpedia

    INDEX
    Explanations

    list item labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mencipt
    0.42
    aturated
    0.39
     nerdy
    0.38
     quién
    0.37
    班牙
    0.37
     misunder
    0.37
     overpowered
    0.37
    __."
    0.37
     да
    0.36
     benar
    0.36
    POSITIVE LOGITS
    또한
    0.40
    Advertisement
    0.38
    During
    0.37
    此外
    0.36
    जबकि
    0.35
     जोकि
    0.34
     દરમિયાન
    0.33
    “”
    0.32
    “
    0.32
     একইভাবে
    0.32
    Act Density 0.037%

    No Known Activations