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

    Neuronpedia

    INDEX
    Explanations

    code commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    als
    -0.08
    icals
    -0.08
    sprech
    -0.07
     geri
    -0.07
     promoter
    -0.07
     promoters
    -0.07
     debt
    -0.07
     richtig
    -0.07
    Zone
    -0.07
     ordentlich
    -0.07
    POSITIVE LOGITS
     Specifies
    0.12
    Provides
    0.10
     Defines
    0.10
     Determines
    0.10
     Indicates
    0.09
     Applies
    0.09
    Defines
    0.09
    用于
    0.09
     Represents
    0.09
     Used
    0.09
    Act Density 0.031%

    No Known Activations