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

    Neuronpedia

    INDEX
    Explanations

    references to various types of mats and matting in different contexts

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

    mats and rugs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elsa
    -0.47
    genstein
    -0.46
     стаття
    -0.46
    kuuta
    -0.43
     Numerade
    -0.43
    JsonProperty
    -0.43
    {}",
    -0.42
    -0.42
    ➋
    -0.42
    SerializeField
    -0.42
    POSITIVE LOGITS
     mats
    1.04
     mat
    0.82
     Mats
    0.71
     tapete
    0.70
     alfombra
    0.70
     rugs
    0.61
    Mats
    0.60
     carpets
    0.59
     tapis
    0.58
     Rugs
    0.56
    Act Density 0.008%

    No Known Activations