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

    Neuronpedia

    INDEX
    Explanations

    proving things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     parent
    0.50
     Parent
    0.49
    parent
    0.46
    Parent
    0.45
    mainwindow
    0.43
    getParent
    0.40
     бать
    0.38
    ParentObject
    0.37
    PARENT
    0.37
     주인
    0.36
    POSITIVE LOGITS
     otras
    0.35
    ági
    0.35
     congrat
    0.34
     other
    0.34
    நீ
    0.33
     congratulate
    0.33
     daughters
    0.33
    erson
    0.32
     everything
    0.32
     daughter
    0.32
    Act Density 0.000%

    No Known Activations