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

    Neuronpedia

    INDEX
    Explanations

    concepts related to control, order, and restraint in various contexts

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

    control, order, discipline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HasFactory
    -0.38
     hjär
    -0.36
    彌
    -0.35
     nakalista
    -0.33
    dol
    -0.31
     ujednoznacz
    -0.31
     Hệ
    -0.31
    جمعیت
    -0.30
     municipalité
    -0.29
     dol
    -0.29
    POSITIVE LOGITS
     restraint
    0.61
    TagMode
    0.60
    CloseOperation
    0.57
    msgTypes
    0.56
     Савезне
    0.56
     noDo
    0.56
     restrained
    0.53
     ExecuteAsync
    0.53
    PyExc
    0.52
    AnchorTagHelper
    0.52
    Act Density 0.078%

    No Known Activations