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

    Neuronpedia

    INDEX
    Explanations

    locations to find

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     गाय
    0.49
     आगामी
    0.46
     Bats
    0.46
    しております
    0.46
    িতি
    0.45
     प्रबंधक
    0.45
    Ap
    0.44
     thighs
    0.44
     textbook
    0.43
    ↵↵↵↵
    0.43
    POSITIVE LOGITS
     grano
    0.59
     aislamiento
    0.57
     inscre
    0.54
    បន្ថ
    0.53
    adihi
    0.52
     окно
    0.52
     Cristó
    0.52
    нор
    0.52
    чь
    0.51
    niveau
    0.51
    Act Density 0.000%

    No Known Activations