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

    Neuronpedia

    INDEX
    Explanations

    travel, budget, interests, preferences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     localized
    0.39
     eclipsed
    0.38
     nun
    0.38
     specular
    0.38
     dashed
    0.38
     rounded
    0.37
    Expr
    0.37
     outline
    0.37
     widespread
    0.37
    хь
    0.37
    POSITIVE LOGITS
     travelling
    0.69
     бюджет
    0.69
     preferring
    0.68
     interesses
    0.67
     предпочита
    0.66
    喜欢
    0.65
    喜歡
    0.65
     preferências
    0.65
     interests
    0.65
    preferences
    0.65
    Act Density 0.011%

    No Known Activations