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

    Neuronpedia

    INDEX
    Explanations

    expressions related to self-indulgence and enjoyment

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

    treating yourself and celebrating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bandeira
    -0.40
     mesmas
    -0.40
     législation
    -0.40
     mochilas
    -0.39
     tatuagens
    -0.37
     dudas
    -0.37
     denuncias
    -0.37
     dúvidas
    -0.37
     résine
    -0.36
     villaggio
    -0.35
    POSITIVE LOGITS
    SequentialGroup
    0.67
     luxurious
    0.63
     للاسماء
    0.62
    UrlResolution
    0.61
    Diweddarwch
    0.60
    ToBounds
    0.59
     luxuri
    0.57
    deluxe
    0.57
     deluxe
    0.57
     luks
    0.57
    Act Density 0.009%

    No Known Activations