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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and matrices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     indul
    0.46
    forecast
    0.40
    indul
    0.40
     solicitado
    0.39
    tanto
    0.38
     conhecer
    0.38
     aconte
    0.38
    बारक
    0.37
     توز
    0.37
    рин
    0.37
    POSITIVE LOGITS
     quaternion
    0.45
    Iterator
    0.38
     fundamental
    0.38
     matrix
    0.38
     subgroups
    0.38
     operators
    0.38
     subgroup
    0.37
     ஐந்து
    0.37
     half
    0.37
     g
    0.37
    Act Density 0.004%

    No Known Activations