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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Edinburgh
    -0.07
     tedbir
    -0.07
     sanitary
    -0.07
     Dover
    -0.07
     Julien
    -0.06
    ि�
    -0.06
    _folder
    -0.06
     Nikon
    -0.06
    depart
    -0.06
    .",↵
    -0.06
    POSITIVE LOGITS
    .And
    0.07
     �
    0.07
     [&
    0.06
     góc
    0.06
     พล
    0.06
     Makes
    0.06
    /MPL
    0.06
     (**
    0.06
     messed
    0.06
    .Page
    0.06
    Act Density 0.016%

    No Known Activations