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

    Neuronpedia

    INDEX
    Explanations

    instances of comparisons and similes in language

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

    treat as if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدیا
    -0.42
    gliere
    -0.41
     study
    -0.40
     Sime
    -0.40
    TextBoxColumn
    -0.40
    inyl
    -0.38
     administrative
    -0.38
    esgue
    -0.38
     berisi
    -0.37
     Joy
    -0.37
    POSITIVE LOGITS
    省市镇
    0.48
    LLocation
    0.46
     lenker
    0.45
     cherchés
    0.44
    BeginContext
    0.43
     Meksiku
    0.41
    \{\\
    0.40
    ſt
    0.39
     <=",
    0.39
     Chriftian
    0.39
    Act Density 0.108%

    No Known Activations