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

    Neuronpedia

    INDEX
    Explanations

    specific dates or years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     capsules
    0.34
     four
    0.32
     droplets
    0.32
     os
    0.30
     kernels
    0.30
     glacier
    0.29
     cakes
    0.29
     clusters
    0.29
     drei
    0.29
     chime
    0.29
    POSITIVE LOGITS
     сотрудни
    0.28
     विवा
    0.28
    have
    0.26
    nego
    0.25
     финансо
    0.25
     финанси
    0.25
    awa
    0.25
    unea
    0.25
     жена
    0.25
     preguntar
    0.24
    Act Density 0.039%

    No Known Activations