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

    Neuronpedia

    INDEX
    Explanations

    themes of abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    0.56
    ed
    0.50
    assembl
    0.49
    uoso
    0.46
    ار
    0.45
    onato
    0.45
    u
    0.45
    athe
    0.45
    view
    0.45
     ஒரு
    0.44
    POSITIVE LOGITS
     socialism
    0.51
     violência
    0.48
     Socialism
    0.45
     depresión
    0.44
     aggression
    0.44
     oor
    0.44
     whakam
    0.44
     putem
    0.44
     censure
    0.43
     fascism
    0.43
    Act Density 0.084%

    No Known Activations