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

    Neuronpedia

    INDEX
    Explanations

    strengths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    raa
    0.56
    ंगाना
    0.55
    উপ
    0.54
     treet
    0.54
     हेल्पलाइन
    0.53
     トップ
    0.52
     soak
    0.52
    ides
    0.52
    csr
    0.51
    hip
    0.51
    POSITIVE LOGITS
    شه
    0.67
    னும்
    0.66
     Surname
    0.65
     Sum
    0.64
    ثم
    0.64
    minLength
    0.63
    あとは
    0.62
     Poi
    0.62
     Stad
    0.62
    ையே
    0.62
    Act Density 0.174%

    No Known Activations