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

    Neuronpedia

    INDEX
    Explanations

    column B, alone, reunite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    東京
    0.45
     jika
    0.45
     cim
    0.43
     película
    0.43
    opencv
    0.43
     modelu
    0.43
    licenses
    0.42
     melon
    0.42
     nếu
    0.42
     concessions
    0.41
    POSITIVE LOGITS
    non
    0.46
     irrever
    0.46
     разнови
    0.45
     inventor
    0.44
     ignored
    0.43
    చర్
    0.42
     Homer
    0.41
     almost
    0.41
     ignore
    0.40
    uden
    0.40
    Act Density 0.004%

    No Known Activations