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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dup
    -0.06
     tecr
    -0.06
    _tracker
    -0.06
    Pale
    -0.06
    Calls
    -0.06
     Hide
    -0.06
    guide
    -0.06
     Pra
    -0.06
     symbols
    -0.06
     noting
    -0.06
    POSITIVE LOGITS
     todo
    0.06
     constitution
    0.06
    이지
    0.06
     رج
    0.06
     лечение
    0.06
    нова
    0.06
    getBytes
    0.06
     hạng
    0.06
    tplib
    0.06
     мая
    0.06
    Act Density 0.021%

    No Known Activations