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

    Neuronpedia

    INDEX
    Explanations

    companies are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     colabor
    0.50
     dhamme
    0.50
     cuyos
    0.48
     warto
    0.47
     value
    0.45
     bilin
    0.44
     sabemos
    0.43
    एनजी
    0.43
    nies
    0.42
    价值
    0.42
    POSITIVE LOGITS
    ukaan
    0.44
     and
    0.43
    iml
    0.42
    alada
    0.42
    ško
    0.41
     تق
    0.40
     دوستان
    0.40
    DESCRIPTION
    0.40
    apixel
    0.39
    amist
    0.39
    Act Density 0.002%

    No Known Activations