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

    Neuronpedia

    INDEX
    Explanations

    answers, bike, vibe, elegant, for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    e
    0.41
    té
    0.41
    ી
    0.41
    c
    0.41
    ប្រទេស
    0.39
    នៃ
    0.39
    或其他
    0.39
    moved
    0.39
    of
    0.38
     испо
    0.38
    POSITIVE LOGITS
     připoj
    0.50
    Says
    0.46
     ensures
    0.46
    Encrypt
    0.45
     எரி
    0.45
     manoeuvre
    0.44
     ateş
    0.43
     കത്തി
    0.42
    Said
    0.42
     którym
    0.42
    Act Density 0.002%

    No Known Activations