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

    Neuronpedia

    INDEX
    Explanations

    key terms and phrases related to reports and summarization

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

    introducing discourse types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.66
    awtextra
    -0.66
    ItemBackground
    -0.65
    AISSEE
    -0.65
     SEDS
    -0.63
    rrggbb
    -0.60
     Italijanski
    -0.58
    ImageContext
    -0.57
    Vidite
    -0.57
    RTDA
    -0.57
    POSITIVE LOGITS
     adet
    0.38
    NSError
    0.36
     виправивши
    0.34
     essi
    0.34
     Parry
    0.33
     Gomes
    0.33
     Shaffer
    0.33
     pot
    0.33
    [(
    0.33
     szy
    0.33
    Act Density 3.382%

    No Known Activations