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

    Neuronpedia

    INDEX
    Explanations

    applying categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sequence
    0.40
    Sequence
    0.40
     Sequence
    0.39
    zczeg
    0.39
     फैमिली
    0.37
     sequence
    0.37
     familia
    0.37
    נד
    0.37
    FAMILY
    0.36
     family
    0.36
    POSITIVE LOGITS
    CategoryImage
    0.41
     hexane
    0.39
     amber
    0.38
    こんにちは
    0.38
    講
    0.38
     représentant
    0.37
     întâ
    0.36
     Kategorie
    0.36
     категорії
    0.36
    ினம்
    0.36
    Act Density 0.000%

    No Known Activations