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

    Neuronpedia

    INDEX
    Explanations

    quoted closing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Usu
    0.35
     radi
    0.34
     sacrifice
    0.33
    Pakistan
    0.33
     धनु
    0.33
     ру
    0.33
     Norwegen
    0.33
     Radi
    0.32
     Deutschland
    0.32
     Iw
    0.32
    POSITIVE LOGITS
     UnitTest
    0.35
    ENCED
    0.31
     IDEA
    0.31
     CFP
    0.30
     indented
    0.29
    AreEqual
    0.29
    美術館
    0.29
    λια
    0.29
    Ფ
    0.29
    isPrime
    0.29
    Act Density 0.069%

    No Known Activations