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

    Neuronpedia

    INDEX
    Explanations

    code blocks and error messages, specifically referencing tensors and matrix operations

    oai_token-act-pair · gemini-2.0-flash

    unique identifiers or keywords

    np_token-act-pair-logits · gpt-4o-mini

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nakalista
    -0.68
    المكان
    -0.62
    ">//
    -0.58
    httphttps
    -0.55
    Искәрмәләр
    -0.54
    :✨
    -0.54
    hasMoreElements
    -0.53
     виправивши
    -0.51
     Eleventh
    -0.51
     ""],
    -0.50
    POSITIVE LOGITS
    BagLayout
    0.49
     tartalomajánló
    0.48
    ريكية
    0.48
    ansha
    0.47
     נד
    0.47
    Portail
    0.45
    ollectionView
    0.45
     ausged
    0.45
    Smiles
    0.45
     eccl
    0.45
    Act Density 1.095%

    No Known Activations