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

    Neuronpedia

    INDEX
    Explanations

    apologize if, Parallelism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    всем
    0.44
     भीती
    0.43
     والث
    0.43
     বুক
    0.42
    eties
    0.42
    镟
    0.41
    Ско
    0.41
     пусты
    0.40
    Gordon
    0.40
     kebut
    0.38
    POSITIVE LOGITS
     回転
    0.43
    ymmetric
    0.40
     contour
    0.38
     towing
    0.37
     rotating
    0.37
    合格
    0.37
    edom
    0.37
     ricor
    0.37
    ญ
    0.36
     Assume
    0.36
    Act Density 0.000%

    No Known Activations