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

    Neuronpedia

    INDEX
    Explanations

    Scientific research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ano
    -1.18
    ANO
    -0.91
    Datuak
    -0.65
    DoubleQuotes
    -0.59
     onCreateView
    -0.55
    UserScript
    -0.54
    WillAppear
    -0.54
    ={`/
    -0.52
     ano
    -0.51
    anos
    -0.50
    POSITIVE LOGITS
     IBOutlet
    0.61
    UBL
    0.55
    AMILTON
    0.53
    break
    0.53
    hank
    0.51
    HAM
    0.48
     harm
    0.48
    PARATOR
    0.47
    ühnen
    0.47
    tices
    0.47
    Act Density 0.012%

    No Known Activations