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

    Neuronpedia

    INDEX
    Explanations

    new followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     consumidores
    0.43
     opnieuw
    0.43
     waardoor
    0.42
     tão
    0.38
     enabled
    0.37
     necessidade
    0.37
     entusias
    0.37
     celebrar
    0.36
     zawier
    0.36
     مراسم
    0.36
    POSITIVE LOGITS
     and
    0.55
    spapers
    0.50
    sw
    0.47
    swire
    0.45
    ترین
    0.45
    spaper
    0.45
    しく
    0.44
    в
    0.44
    foundland
    0.44
    ತನ
    0.43
    Act Density 0.024%

    No Known Activations