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

    Neuronpedia

    INDEX
    Explanations

    up to responsibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     capacit
    0.39
    ε
    0.38
     parasit
    0.38
     vines
    0.38
    жер
    0.38
     feathers
    0.37
    ঋ
    0.37
     înviat
    0.37
     hues
    0.36
     centrality
    0.35
    POSITIVE LOGITS
     onus
    1.38
     responsibility
    1.33
     Responsibility
    1.29
     responsabilidad
    1.20
    responsibility
    1.10
     Verantwortung
    1.09
     जिम्मेदारी
    1.07
     responsabilité
    1.06
     responsabilità
    1.06
    责任
    1.02
    Act Density 0.016%

    No Known Activations