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

    Neuronpedia

    INDEX
    Explanations

    hidden or secret

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    镳
    0.67
    উন
    0.67
    বাব
    0.66
    ánica
    0.65
    સમ
    0.65
    жор
    0.62
     জের
    0.60
    iotic
    0.60
    comparator
    0.60
    槊
    0.60
    POSITIVE LOGITS
     hidden
    5.10
    hidden
    4.52
     Hidden
    4.41
    Hidden
    4.39
     concealed
    4.30
    隐藏
    3.99
     hiding
    3.89
     secret
    3.80
     nascost
    3.76
     скры
    3.68
    Act Density 1.561%

    No Known Activations