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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bindung
    -0.08
     kinase
    -0.07
    遗迹
    -0.07
    倮
    -0.07
     deg
    -0.07
    :"#
    -0.07
    俫
    -0.07
    唬
    -0.06
    �
    -0.06
    _thread
    -0.06
    POSITIVE LOGITS
    一边
    0.08
    -books
    0.07
    orque
    0.07
     Aleppo
    0.07
    tó
    0.07
    +\
    0.06
    αι
    0.06
    {}.
    0.06
    嫂
    0.06
    ject
    0.06
    Act Density 0.006%

    No Known Activations