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

    Neuronpedia

    INDEX
    Explanations

    concepts related to loyalty and commitment

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

    reliance on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нрави
    -0.47
    atigable
    -0.43
    prevState
    -0.40
    baguna
    -0.40
    itinéraire
    -0.40
     nhàng
    -0.39
     estimés
    -0.39
    iae
    -0.39
     gustó
    -0.39
    MessageState
    -0.38
    POSITIVE LOGITS
    setVerticalGroup
    0.55
     myſelf
    0.54
    AddTagHelper
    0.53
     faſt
    0.52
     fubject
    0.51
    DrawerToggle
    0.51
     ujednoznacz
    0.51
     chofe
    0.50
     anſ
    0.49
    httphttps
    0.48
    Act Density 0.045%

    No Known Activations