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

    Neuronpedia

    INDEX
    Explanations

    connection and callback assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಾನೆ
    0.28
    पाउंड
    0.28
    ৪০
    0.27
    াণী
    0.27
    ,…
    0.27
    anceled
    0.27
    Fluid
    0.27
    Utc
    0.26
    娩
    0.26
    🕚
    0.26
    POSITIVE LOGITS
     tih
    0.28
     &
    0.27
     amac
    0.26
     beneficia
    0.26
     Ct
    0.25
     vitt
    0.25
     ilus
    0.24
     eth
    0.24
     vedit
    0.24
     als
    0.23
    Act Density 0.230%

    No Known Activations