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

    Neuronpedia

    INDEX
    Explanations

    creating, constructing, prototypes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     così
    0.24
    𝖓
    0.23
     mie
    0.22
     merupakan
    0.22
    ```
    0.22
     cosi
    0.22
    Regards
    0.22
     entren
    0.21
    કો
    0.21
    大会
    0.21
    POSITIVE LOGITS
    doped
    0.29
    cules
    0.28
     LMFBR
    0.26
    leine
    0.25
    Ꞌ
    0.24
    diaz
    0.23
     ATC
    0.23
    رسٹ
    0.23
    ths
    0.23
     EIR
    0.23
    Act Density 1.124%

    No Known Activations