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

    Neuronpedia

    INDEX
    Explanations

    nature or topic of content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    0.47
     که
    0.45
    ஸ்
    0.45
    )
    0.43
    ス
    0.43
    kład
    0.42
    琀
    0.42
     said
    0.41
    í
    0.40
    är
    0.40
    POSITIVE LOGITS
     Bahkan
    0.45
     youll
    0.45
    Ꮠ
    0.45
    Mein
    0.43
    Sono
    0.43
     Somit
    0.43
     ඔබට
    0.42
     ytter
    0.42
     confuses
    0.42
    c
    0.41
    Act Density 0.397%

    No Known Activations