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

    Neuronpedia

    INDEX
    Explanations

    explain an

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enggak
    0.76
     și
    0.72
     savor
    0.72
     Afterward
    0.71
     flavorful
    0.70
    Neighbors
    0.66
     grayish
    0.66
     определён
    0.65
     लड़कियों
    0.64
     ș
    0.64
    POSITIVE LOGITS
    Whilst
    1.73
     Whilst
    1.68
     whilst
    1.58
     utilises
    1.34
     utilising
    1.32
     standardised
    1.25
     optimisation
    1.23
     optimise
    1.23
     utilise
    1.21
     realise
    1.20
    Act Density 0.045%

    No Known Activations