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

    Neuronpedia

    INDEX
    Explanations

    math and science courses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    কারী
    0.33
     रूप
    0.30
    ties
    0.30
    aten
    0.30
     Республи
    0.29
    Ы
    0.28
    دى
    0.28
    剂
    0.28
    re
    0.28
    ł
    0.28
    POSITIVE LOGITS
     CMB
    0.34
    ка
    0.32
     textbooks
    0.32
    พาะ
    0.32
    $-$
    0.31
     thermodynamics
    0.31
     Kirchhoff
    0.31
    KT
    0.31
     cruciate
    0.30
     startIndex
    0.30
    Act Density 0.234%

    No Known Activations