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

    Neuronpedia

    INDEX
    Explanations

    code structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     соп
    -0.06
     Japanese
    -0.06
     internals
    -0.06
     semaphore
    -0.06
    (ship
    -0.06
     accents
    -0.06
    WriteBarrier
    -0.06
    Highlighted
    -0.06
     Hearth
    -0.06
     ذکر
    -0.05
    POSITIVE LOGITS
    віль
    0.07
    0.07
    0.06
     Article
    0.06
    .then
    0.06
    .master
    0.06
    0.06
     Deploy
    0.06
     Prepare
    0.06
    _wrap
    0.06
    Act Density 0.009%

    No Known Activations