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

    Neuronpedia

    INDEX
    Explanations

    references to rugs and carpet-related items

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

    rug

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Autorisations
    -0.47
    issen
    -0.47
    openSession
    -0.44
    isSuccessful
    -0.40
    AddWithValue
    -0.40
    awaiter
    -0.39
    Composable
    -0.39
     Tempo
    -0.39
     comuniques
    -0.39
     Dele
    -0.38
    POSITIVE LOGITS
     rug
    2.33
     Rug
    2.17
    Rug
    1.95
     rugs
    1.92
     Rugs
    1.78
    rug
    1.70
    rugs
    1.32
     Rugg
    1.26
     Ruger
    0.99
    carpet
    0.87
    Act Density 0.001%

    No Known Activations