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

    Neuronpedia

    INDEX
    Explanations

    strings of words expressing degree or intensity, as well as abstract concepts like imagination.

    oai_token-act-pair · gemini-2.0-flash

    same

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AssemblyProduct
    -0.71
    SequentialGroup
    -0.71
    ReusableCell
    -0.63
    DataAnnotations
    -0.60
     BoxFit
    -0.59
    ollectionView
    -0.56
    awaiter
    -0.54
    WireFormat
    -0.53
    deltaTime
    -0.52
    Климат
    -0.52
    POSITIVE LOGITS
     same
    1.20
    Same
    1.16
    same
    1.11
     like
    1.09
     Same
    1.05
     samma
    0.98
     dezelfde
    0.96
     samme
    0.93
     mismos
    0.86
     mismo
    0.85
    Act Density 1.442%

    No Known Activations