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

    Neuronpedia

    INDEX
    Explanations

    java package names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒈠
    0.47
    getMainUI
    0.44
    詁
    0.43
    LOLL
    0.41
    洨
    0.40
    ANGMAR
    0.40
    ับสนุน
    0.39
    𒅁
    0.39
    বিষ্য
    0.39
    ServiceGroupID
    0.39
    POSITIVE LOGITS
    -
    0.47
    .
    0.44
    T
    0.38
    _
    0.36
     Hua
    0.35
     in
    0.35
     Media
    0.34
    man
    0.34
     T
    0.33
     -
    0.33
    Act Density 0.000%

    No Known Activations