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

    Neuronpedia

    INDEX
    Explanations

    world, primary, physics, locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     activate
    0.44
     kJ
    0.41
     activated
    0.40
     Activated
    0.39
     Awake
    0.39
     Activate
    0.38
     activates
    0.38
     BorderRadius
    0.38
     userId
    0.37
     ಪರಿ
    0.37
    POSITIVE LOGITS
    munderover
    0.44
    يبقى
    0.44
     invertebr
    0.42
    irnya
    0.41
    leaves
    0.40
     dibangun
    0.39
    мите
    0.39
    Built
    0.39
    ずる
    0.39
     perempuan
    0.38
    Act Density 0.001%

    No Known Activations