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

    Neuronpedia

    INDEX
    Explanations

    code snippets that use mathematical functions or operations

    oai_token-act-pair · gemini-2.0-flash

    Math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.44
    ItemBackground
    -0.56
     néz
    -0.55
    ıştır
    -0.54
    Geplaatst
    -0.54
     mukana
    -0.53
     kiin
    -0.53
    BeginContext
    -0.53
     sää
    -0.52
    GenerationType
    -0.51
    POSITIVE LOGITS
    AddTagHelper
    0.75
    principalTable
    0.63
     combineReducers
    0.53
     상세
    0.48
    )}_
    0.48
    MemoryWarning
    0.47
     "..\..\..\
    0.46
     "..\..\
    0.44
    नलिखित
    0.43
    setVerticalGroup
    0.42
    Act Density 16.630%

    No Known Activations