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

    Neuronpedia

    INDEX
    Explanations

    stats

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     loaders
    -0.07
    .Json
    -0.07
    ummer
    -0.06
    탄
    -0.06
     shields
    -0.06
     meeting
    -0.06
     marked
    -0.06
     membranes
    -0.06
    -cli
    -0.06
     unspecified
    -0.06
    POSITIVE LOGITS
    一点
    0.06
     Attributes
    0.06
     очі
    0.06
     Titles
    0.06
    Chuck
    0.06
    /ioutil
    0.06
    /",↵
    0.06
     点
    0.06
    .readline
    0.06
    /ayushman
    0.05
    Act Density 0.006%

    No Known Activations