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

    Neuronpedia

    INDEX
    Explanations

    href

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ulta
    -0.07
    .flag
    -0.07
     Plato
    -0.07
    /course
    -0.06
     trat
    -0.06
    track
    -0.06
     Pract
    -0.06
    uite
    -0.06
    okit
    -0.06
    JUnit
    -0.06
    POSITIVE LOGITS
     bis
    0.07
     href
    0.07
    ẳng
    0.06
    _NV
    0.06
    _dbg
    0.06
     Baba
    0.06
    .Navigate
    0.06
     Kag
    0.06
    (vertices
    0.06
     Bis
    0.06
    Act Density 0.001%

    No Known Activations