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

    Neuronpedia

    INDEX
    Explanations

    creating templates and apps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !),
    0.46
    .):
    0.45
    leyen
    0.45
    layan
    0.44
    :'',
    0.43
    ...),
    0.42
    tram
    0.42
    Bien
    0.42
    र
    0.41
    atoms
    0.41
    POSITIVE LOGITS
     \$
    0.56
     ευρώ
    0.47
     ロング
    0.46
     www
    0.45
     isbn
    0.45
    ","-
    0.44
     </
    0.44
     ./
    0.44
    带来
    0.43
     nws
    0.43
    Act Density 0.108%

    No Known Activations