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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a state of being or existence related to posing or representing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    posing or presenting threats/challenges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    basicConfig
    -0.60
     continúas
    -0.59
     ویکی‌پدی
    -0.57
    ChildScrollView
    -0.57
    MethodManager
    -0.56
    indelijk
    -0.53
     administrativa
    -0.50
    Württemberg
    -0.49
     المعيارى
    -0.48
     échange
    -0.47
    POSITIVE LOGITS
     Pose
    1.05
    Pose
    1.02
     pose
    1.02
     posing
    0.94
    pose
    0.90
     posed
    0.88
    POSE
    0.86
     poses
    0.82
     poser
    0.68
     posé
    0.66
    Act Density 0.010%

    No Known Activations