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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jack
    -0.06
     Bits
    -0.06
    idity
    -0.06
     bottleneck
    -0.06
     Raj
    -0.06
     lorsque
    -0.06
     Bulls
    -0.06
     curl
    -0.06
     Bale
    -0.06
     ICO
    -0.06
    POSITIVE LOGITS
    _man
    0.07
    	true
    0.07
     wirk
    0.06
    фек
    0.06
    `(
    0.06
    ]init
    0.06
     얻
    0.06
     DOES
    0.06
     ทำ
    0.06
    =YES
    0.06
    Act Density 0.000%

    No Known Activations