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

    Neuronpedia

    INDEX
    Explanations

    right

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ンス
    -0.06
    _ITEM
    -0.06
     chests
    -0.06
     annon
    -0.06
    cup
    -0.06
    жень
    -0.06
    >\↵
    -0.06
     ženy
    -0.06
     chewing
    -0.06
     grain
    -0.06
    POSITIVE LOGITS
    getSimpleName
    0.06
    _sock
    0.06
     Disaster
    0.06
     fg
    0.06
    	lbl
    0.06
    feeds
    0.06
    upid
    0.06
    ecektir
    0.06
    warts
    0.06
     provoke
    0.06
    Act Density 0.001%

    No Known Activations