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

    Neuronpedia

    INDEX
    Explanations

    starting or beginning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ioon
    1.23
     aspectos
    1.19
    भीत
    1.14
    esus
    1.13
     İstifadə
    1.13
    ivé
    1.12
    writeInt
    1.11
     inserts
    1.11
    ucky
    1.11
     Aspect
    1.10
    POSITIVE LOGITS
    swith
    1.33
     координат
    1.31
    OfDay
    1.26
    le
    1.25
    xref
    1.24
    BitCount
    1.18
    ிய
    1.18
    呪
    1.17
    ্রম
    1.12
    の頃
    1.10
    Act Density 0.284%

    No Known Activations