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

    Neuronpedia

    INDEX
    Explanations

    introducing concepts or definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ano
    0.37
    lined
    0.36
    adem
    0.36
    ınd
    0.34
    ública
    0.33
    atters
    0.33
     他们
    0.33
    uiDesigner
    0.33
    fueled
    0.33
    bs
    0.33
    POSITIVE LOGITS
     waarbij
    0.53
     whereby
    0.50
     với
    0.49
     waarin
    0.46
     prevede
    0.44
     עם
    0.43
     avec
    0.42
     wherein
    0.42
     dengan
    0.40
     privind
    0.40
    Act Density 3.023%

    No Known Activations