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

    Neuronpedia

    INDEX
    Explanations

    specific health-related categories and their associated attributes or conditions

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

    category names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ब्रेकडाउन
    -0.48
     linkovi
    -0.44
    delwed
    -0.43
    ± 
    -0.42
    舺
    -0.40
    bobox
    -0.39
     مرئيه
    -0.38
     rink
    -0.38
    حوالہ
    -0.37
     continúas
    -0.37
    POSITIVE LOGITS
     område
    0.66
    forChild
    0.59
     subcategory
    0.52
     category
    0.49
    SpringBootTest
    0.47
     doInBackground
    0.47
    IsMutable
    0.46
     createSlice
    0.46
    områ
    0.46
     såsom
    0.46
    Act Density 0.147%

    No Known Activations