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

    Neuronpedia

    INDEX
    Explanations

    path

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unce
    -0.08
    mue
    -0.07
     moder
    -0.07
     undermin
    -0.06
    Ye
    -0.06
     deco
    -0.06
    Ve
    -0.06
     dec
    -0.06
     fre
    -0.06
     Dre
    -0.06
    POSITIVE LOGITS
     Path
    0.13
     path
    0.12
    Path
    0.11
    .Path
    0.10
     Paths
    0.10
     paths
    0.10
    path
    0.09
    -path
    0.09
    Paths
    0.09
    _PATH
    0.09
    Act Density 0.046%

    No Known Activations