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

    Neuronpedia

    INDEX
    Explanations

    process of perception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     leurs
    0.45
    LLCATS
    0.44
     vielä
    0.44
     kredit
    0.44
     policías
    0.44
     revolutionaries
    0.43
     diffract
    0.43
     lectores
    0.43
     dracon
    0.43
     campionato
    0.42
    POSITIVE LOGITS
     способность
    0.60
     способности
    0.53
     ability
    0.50
     определение
    0.47
     Verme
    0.45
    efined
    0.44
     perceiving
    0.43
    的过程
    0.43
    implies
    0.43
     Perception
    0.43
    Act Density 0.231%

    No Known Activations