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

    Neuronpedia

    INDEX
    Explanations

    sentences that describe business activities or government functions

    oai_token-act-pair · gemini-2.0-flash

    has/have

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yet
    -1.14
    yet
    -1.05
     YET
    -0.94
    NameInMap
    -0.91
     Yet
    -0.90
    Yet
    -0.89
    SourceChecksum
    -0.81
    DockStyle
    -0.75
    ValueStyle
    -0.74
    LookAnd
    -0.72
    POSITIVE LOGITS
     carico
    0.62
    binden
    0.48
     TAMBÉM
    0.46
     leſs
    0.46
    AnchorTagHelper
    0.46
    ={`/
    0.45
    îner
    0.44
     naturen
    0.44
    ArgumentParser
    0.43
    djangoproject
    0.43
    Act Density 7.917%

    No Known Activations