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

    Neuronpedia

    INDEX
    Explanations

    65

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    passes
    -0.07
     StObject
    -0.06
     Khu
    -0.06
    .BOLD
    -0.06
    ittal
    -0.06
     delet
    -0.06
     niệm
    -0.06
    .reg
    -0.06
     Zhao
    -0.06
    No
    -0.06
    POSITIVE LOGITS
    云
    0.07
     北京
    0.06
     ░
    0.06
    deer
    0.06
     yüksel
    0.06
     Bridges
    0.05
    188
    0.05
    _Pl
    0.05
     Lent
    0.05
    ('^
    0.05
    Act Density 0.018%

    No Known Activations