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

    Neuronpedia

    INDEX
    Explanations

    video tutorials or courses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अनजान
    0.47
     रीति
    0.46
     perturbation
    0.46
     hybridization
    0.45
     pemerintahan
    0.44
     सभ्यता
    0.43
    機の
    0.42
    ForRule
    0.42
     timeouts
    0.42
     रोजिक
    0.42
    POSITIVE LOGITS
    d
    0.52
    e
    0.39
    rains
    0.39
    يش
    0.38
    يث
    0.38
    جميع
    0.38
     we
    0.38
     and
    0.38
    elijk
    0.38
    '
    0.38
    Act Density 0.001%

    No Known Activations