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

    Neuronpedia

    INDEX
    Explanations

    rise and its combinations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lifting
    0.80
    Elev
    0.77
     elevating
    0.77
     lifted
    0.73
    elev
    0.73
     Lifting
    0.73
     رفع
    0.72
     élevés
    0.72
     mengangkat
    0.72
     lift
    0.71
    POSITIVE LOGITS
    ann
    0.44
     averted
    0.43
     assol
    0.43
    INIS
    0.41
     slower
    0.41
     backstory
    0.40
     schnell
    0.39
     Anglia
    0.39
     pp
    0.39
    COOK
    0.39
    Act Density 0.008%

    No Known Activations