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

    Neuronpedia

    INDEX
    Explanations

    text that describes items arranged in a particular sequence

    oai_token-act-pair · gemini-2.0-flash

    ordering items

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    XmlAccessorType
    -0.82
    sidemargin
    -0.76
    TintMode
    -0.73
     "..\..\..\
    -0.68
     fubject
    -0.64
     snippetHide
    -0.63
    ListItemIcon
    -0.62
    NUMX
    -0.62
    IndentedString
    -0.62
    IVersion
    -0.61
    POSITIVE LOGITS
     متعلقه
    0.52
    Personendaten
    0.47
     lenker
    0.47
    ag
    0.45
    же
    0.45
    part
    0.45
    割
    0.44
    hy
    0.43
    تين
    0.42
    pril
    0.41
    Act Density 7.036%

    No Known Activations