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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     phát
    -0.08
     Hel
    -0.08
     सफल
    -0.07
    .vaadin
    -0.07
    奋
    -0.07
    ởi
    -0.07
     Hun
    -0.07
    velocity
    -0.07
     शानदार
    -0.07
    .preview
    -0.07
    POSITIVE LOGITS
     parentheses
    0.17
    括
    0.14
     grouping
    0.13
     precedence
    0.13
     ambiguity
    0.12
     brackets
    0.12
     ambiguous
    0.12
     parsed
    0.11
    Grouping
    0.11
     bracket
    0.10
    Act Density 0.041%

    No Known Activations