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

    Neuronpedia

    INDEX
    Explanations

    g

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fort
    -0.06
           
    -0.06
    /DTD
    -0.06
     misunderstanding
    -0.06
     مرات
    -0.06
     hwnd
    -0.06
     itemId
    -0.06
    _FIRE
    -0.06
    XD
    -0.06
     pad
    -0.06
    POSITIVE LOGITS
    g
    0.10
    (g
    0.10
     g
    0.09
     manned
    0.08
    -g
    0.08
    /gl
    0.07
    G
    0.07
     G
    0.07
    면서
    0.07
     gaz
    0.07
    Act Density 0.010%

    No Known Activations