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

    Neuronpedia

    INDEX
    Explanations

    explain simply

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     somewhat
    0.45
     нюан
    0.45
     nuances
    0.45
     subtleties
    0.44
     nuance
    0.43
     embrace
    0.43
     mysterious
    0.43
     perfecting
    0.41
     intricacies
    0.41
     nuanced
    0.40
    POSITIVE LOGITS
     simplification
    0.98
     سادہ
    0.98
     simpler
    0.95
     simplified
    0.93
    simple
    0.91
     Simplify
    0.89
     simplicity
    0.88
     simpl
    0.88
     sencillo
    0.88
     SIMPLE
    0.87
    Act Density 0.142%

    No Known Activations