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

    Neuronpedia

    INDEX
    Explanations

    math or code context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ॉल
    0.42
    ικής
    0.41
    gifter
    0.38
    Sens
    0.38
    ባ
    0.38
    тивного
    0.37
    Puedes
    0.37
    الأ
    0.37
    毫
    0.37
    зге
    0.37
    POSITIVE LOGITS
     Lobo
    0.40
    தள
    0.40
     distanza
    0.39
     mappa
    0.38
     Estrada
    0.38
     സ്വാ
    0.38
     libr
    0.38
     progetto
    0.37
     opposes
    0.37
     Här
    0.37
    Act Density 0.000%

    No Known Activations