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

    Neuronpedia

    INDEX
    Explanations

    specific version or lengthy summary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scienza
    0.44
     bhuv
    0.43
     vectors
    0.42
     upas
    0.42
    сна
    0.42
     vector
    0.41
    сну
    0.40
     namin
    0.40
     exclusivamente
    0.40
     ausschließlich
    0.40
    POSITIVE LOGITS
    और
    0.39
    _{\
    0.39
    y
    0.39
    時間が
    0.38
    \$
    0.37
    データの
    0.37
    及び
    0.36
    \
    0.36
     ストレ
    0.36
    SupportPackage
    0.36
    Act Density 0.001%

    No Known Activations