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

    Neuronpedia

    INDEX
    Explanations

    To help me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ৫৭
    1.18
     tasked
    1.17
     duis
    1.13
    kmeans
    1.09
    ことを
    1.08
    garakan
    1.06
     excels
    1.05
     importantly
    1.04
     됩니다
    1.04
    Ма
    1.03
    POSITIVE LOGITS
    in
    1.38
    or
    1.17
     së
    1.15
    lere
    1.14
    ே
    1.13
     বিচার
    1.11
    renia
    1.10
     extremity
    1.09
    ản
    1.08
    avoid
    1.06
    Act Density 0.042%

    No Known Activations