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

    Neuronpedia

    INDEX
    Explanations

    HTML

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Numbers
    -0.07
     TJ
    -0.07
    材
    -0.06
    “And
    -0.06
     Tig
    -0.06
     swelling
    -0.06
    非
    -0.06
     AQ
    -0.06
     JPanel
    -0.06
     команди
    -0.06
    POSITIVE LOGITS
    Zen
    0.06
    ~-
    0.06
    APSHOT
    0.06
    iedo
    0.06
    .scheduler
    0.06
     interess
    0.06
     geopol
    0.06
    št
    0.06
    ایت
    0.06
    snapshot
    0.06
    Act Density 0.162%

    No Known Activations