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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SPECIAL
    -0.07
    \Field
    -0.07
    wh
    -0.06
    Typed
    -0.06
     тоді
    -0.06
    (Q
    -0.06
    charted
    -0.06
     phòng
    -0.06
    ิเคราะห
    -0.06
    -black
    -0.06
    POSITIVE LOGITS
     training
    0.07
     SALE
    0.07
     Glas
    0.07
    MainWindow
    0.06
    Copy
    0.06
    ักงาน
    0.06
     None
    0.06
     fichier
    0.06
    ))
    0.06
    zení
    0.06
    Act Density 0.036%

    No Known Activations