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

    Neuronpedia

    INDEX
    Explanations

    GoogleTest framework

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sikre
    0.43
    oyen
    0.42
    यत
    0.42
     ganzen
    0.41
    hey
    0.41
     спосо
    0.40
     Ayala
    0.40
    ones
    0.39
    łego
    0.39
    yen
    0.39
    POSITIVE LOGITS
     Dise
    0.50
     descom
    0.45
     Lei
    0.45
     rapporto
    0.45
     CaCl
    0.45
     dise
    0.45
    ᱱ
    0.45
     なり
    0.44
    ]}$
    0.44
    ナトリウム
    0.43
    Act Density 0.000%

    No Known Activations