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

    Neuronpedia

    INDEX
    Explanations

    using or shaping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pauper
    0.48
     otot
    0.46
     genealog
    0.45
     catar
    0.44
     sardines
    0.44
     daffodils
    0.43
     publicados
    0.43
     tubs
    0.42
     cranberries
    0.42
    вут
    0.41
    POSITIVE LOGITS
     Forecasting
    0.47
     Using
    0.47
     Utilizing
    0.46
     This
    0.44
     Planning
    0.43
     Were
    0.43
     Estimation
    0.43
     활용
    0.42
     وحتى
    0.42
     Assuming
    0.42
    Act Density 0.000%

    No Known Activations