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

    Neuronpedia

    INDEX
    Explanations

    checklist items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sgd
    0.50
     okaz
    0.43
    urdu
    0.42
    atay
    0.42
    ા
    0.42
    ée
    0.41
    eek
    0.41
    িকে
    0.41
    segaretro
    0.41
     coffers
    0.41
    POSITIVE LOGITS
     и
    0.45
    憎
    0.44
     Android
    0.44
     Halloween
    0.43
     VARIABLE
    0.42
     relatively
    0.41
     избира
    0.41
     AWS
    0.40
    लेश
    0.40
     berkembang
    0.39
    Act Density 0.001%

    No Known Activations