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

    Neuronpedia

    INDEX
    Explanations

    way of doing things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    りたい
    0.35
    ```
    0.35
    ंचा
    0.34
     Der
    0.33
     Maz
    0.33
    Maz
    0.33
    ských
    0.33
    Tak
    0.33
     Ball
    0.32
     Partners
    0.32
    POSITIVE LOGITS
     maneras
    0.44
     kuidas
    0.40
     để
    0.39
     waarop
    0.38
     maneiras
    0.37
    衡量
    0.36
     dampen
    0.35
     कहने
    0.35
     ஆண்டுகளில்
    0.35
    ដើម្បី
    0.35
    Act Density 0.012%

    No Known Activations