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

    Neuronpedia

    INDEX
    Explanations

    words related to politics, laws, and policies

    oai_token-act-pair · gemini-2.0-flash

    Law and politics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.57
    AddHtmlAttribute
    -0.55
    <bos>
    -0.52
     AssemblyProduct
    -0.52
    liflower
    -0.51
    oneofs
    -0.49
     Meksiku
    -0.48
    rungsseite
    -0.47
    ⓧ
    -0.47
    GEBURTS
    -0.46
    POSITIVE LOGITS
    ATEGORIES
    0.59
    ftant
    0.58
    CompleteListener
    0.55
     contextLoads
    0.54
    ondern
    0.54
    gorithm
    0.54
    לום
    0.53
     Tampoco
    0.52
     CHAPITRE
    0.52
     tabindex
    0.52
    Act Density 1.864%

    No Known Activations