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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "this."

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

    object-oriented code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.60
    RTGC
    -0.56
     ligiloj
    -0.53
    PreExecute
    -0.51
     queſta
    -0.51
     ***!
    -0.50
    ➯
    -0.50
    tableFuture
    -0.49
    domada
    -0.49
     مرئيه
    -0.49
    POSITIVE LOGITS
     antidesliz
    0.34
     rempli
    0.33
    close
    0.33
     idéia
    0.32
     pensamiento
    0.32
    Ibid
    0.32
     Ibid
    0.32
     lèvres
    0.32
     Eing
    0.32
     ricev
    0.32
    Act Density 0.004%

    No Known Activations