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

    Neuronpedia

    INDEX
    Explanations

    evaluating without hype

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     applies
    0.42
     Hansen
    0.42
     applic
    0.41
     rebates
    0.41
     Au
    0.40
     Yep
    0.39
     Vienne
    0.38
     Applic
    0.38
     decreases
    0.37
     Warp
    0.37
    POSITIVE LOGITS
    ····
    0.41
    ReadKey
    0.39
    精心
    0.38
     agrí
    0.38
    ვა
    0.38
    abila
    0.38
    กาย
    0.38
     serif
    0.37
     cultivos
    0.37
    ･･
    0.37
    Act Density 0.000%

    No Known Activations