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

    Neuronpedia

    INDEX
    Explanations

    exclus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bonded
    -0.08
     theoret
    -0.08
     Kend
    -0.07
    (tableName
    -0.07
     wallpapers
    -0.07
     方
    -0.07
     rů
    -0.07
     Born
    -0.07
    (PARAM
    -0.07
    TreeNode
    -0.07
    POSITIVE LOGITS
     Ex
    0.10
    Ex
    0.08
    _Ex
    0.08
     exhibitions
    0.08
    ex
    0.08
    .ex
    0.08
     Exhib
    0.08
     ex
    0.08
    X
    0.07
    XH
    0.07
    Act Density 0.126%

    No Known Activations