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

    Neuronpedia

    INDEX
    Explanations

    boasts and provides features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sarebbero
    0.52
     whereby
    0.49
     indiquant
    0.48
     seraient
    0.46
     दिखाने
    0.43
     auraient
    0.43
    籲
    0.43
     WOULD
    0.43
    issaient
    0.42
    ']].
    0.41
    POSITIVE LOGITS
     boasts
    1.38
     offers
    1.37
     combines
    1.05
     boast
    1.05
     provides
    1.02
    offers
    0.99
     oferece
    0.98
     biedt
    0.98
     excels
    0.97
     bietet
    0.96
    Act Density 0.117%

    No Known Activations