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

    Neuronpedia

    INDEX
    Explanations

    poetry and AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    និយាយ
    0.48
    akkhati
    0.48
     introducción
    0.46
    onomi
    0.46
    હાસ
    0.44
    িয়াছিল
    0.44
     unterschied
    0.43
     পিঁপড়ার
    0.43
     introduit
    0.43
    ழிய
    0.42
    POSITIVE LOGITS
     AI
    0.46
     TI
    0.44
    ↵
    0.41
    Since
    0.40
     AF
    0.40
    .
    0.40
     I
    0.39
    :(
    0.38
     ISO
    0.38
    .|
    0.38
    Act Density 0.001%

    No Known Activations