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

    Neuronpedia

    INDEX
    Explanations

    affordability, optimized articles, shorteners, sizeof

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hun
    0.52
    3
    0.49
    ut
    0.48
    Mild
    0.48
    hung
    0.47
    King
    0.47
    Morning
    0.47
    where
    0.46
    Muk
    0.46
    Mask
    0.46
    POSITIVE LOGITS
     scuola
    0.53
     partecipazione
    0.52
     trabalho
    0.52
     coopération
    0.51
     cambiamento
    0.50
     rinnov
    0.49
     renovación
    0.49
     문화
    0.49
     responsabilidad
    0.48
    ιασ
    0.48
    Act Density 0.000%

    No Known Activations