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

    Neuronpedia

    INDEX
    Explanations

    arte, arquitectura, cultura, cocina

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     brick
    0.47
     bowel
    0.47
     beck
    0.44
     malignancy
    0.44
    ’
    0.44
     ännu
    0.44
     seiner
    0.43
     ship
    0.42
     Freud
    0.42
     bottom
    0.42
    POSITIVE LOGITS
    ၁
    0.61
    ক
    0.55
     ricerca
    0.54
    ay
    0.53
    ativos
    0.53
    switching
    0.53
    ك
    0.53
    ။
    0.53
    ል።
    0.52
    திகள்
    0.52
    Act Density 0.000%

    No Known Activations