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

    Neuronpedia

    INDEX
    Explanations

    code related to UI click listeners and dialog boxes

    oai_token-act-pair · gemini-2.0-flash

    code implementations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.81
     Waray
    -0.63
     religieuses
    -0.63
     raiſ
    -0.63
     ſer
    -0.62
     Offisielt
    -0.60
     auffi
    -0.60
    TemporalType
    -0.60
     obſ
    -0.59
     purpoſe
    -0.58
    POSITIVE LOGITS
     의
    0.43
     Biôgrafia
    0.43
    IInterface
    0.43
     sosten
    0.42
    Xamarin
    0.42
    menter
    0.42
     l
    0.40
    chyma
    0.40
     suspend
    0.40
    EndGlobalSection
    0.40
    Act Density 0.590%

    No Known Activations