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

    Neuronpedia

    INDEX
    Explanations

    right and absolutely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     څخه
    0.43
    乎
    0.43
    ạng
    0.40
    raphic
    0.40
    ி
    0.39
     лінії
    0.38
    ここで
    0.38
     ``
    0.38
     הרבה
    0.38
    ीय
    0.37
    POSITIVE LOGITS
    Unlimited
    0.42
     امیر
    0.39
     Angelica
    0.39
     Davey
    0.38
     withdraw
    0.38
    speedboat
    0.37
     Tavares
    0.37
    century
    0.37
    尻
    0.37
     uninterrupted
    0.37
    Act Density 0.000%

    No Known Activations