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

    Neuronpedia

    INDEX
    Explanations

    legal claims or patent claims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     -
    -2.77
    на
    -2.31
     $
    -2.28
     Some
    -2.27
     That
    -2.25
     criticize
    -2.20
     étude
    -2.20
    媄
    -2.19
     April
    -2.19
     Whether
    -2.17
    POSITIVE LOGITS
    3.09
    橚
    2.80
    냑
    2.69
    蹀
    2.47
    ⸫
    2.45
    er
    2.44
    ейчас
    2.42
    之为
    2.33
     інші
    2.28
    最为
    2.28
    Act Density 0.015%

    No Known Activations