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

    Neuronpedia

    INDEX
    Explanations

    generally followed by description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    0.70
     are
    0.64
    '
    0.61
    ray
    0.57
    )
    0.54
     to
    0.53
    োজেন
    0.52
     a
    0.52
    aka
    0.50
    ambahan
    0.50
    POSITIVE LOGITS
    رر
    0.60
    भीर
    0.58
    is
    0.55
    ти
    0.54
     frivol
    0.54
    이트
    0.54
    무리
    0.54
    दित
    0.54
    iune
    0.54
    indruck
    0.53
    Act Density 0.004%

    No Known Activations