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

    Neuronpedia

    INDEX
    Explanations

    government and law concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anecdotal
    0.78
     gritty
    0.73
     brainstorming
    0.72
     subtle
    0.72
     uptick
    0.70
     synaptic
    0.69
     choppy
    0.69
     onboarding
    0.68
     sneaky
    0.67
     serendip
    0.66
    POSITIVE LOGITS
     consag
    1.04
     enshrined
    1.02
     envisaged
    1.00
     conformément
    0.96
     pursuant
    0.89
     enshr
    0.88
     garantizar
    0.87
     garante
    0.85
     vis
    0.84
     commensurate
    0.84
    Act Density 0.057%

    No Known Activations