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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Release
    -0.07
    rl
    -0.07
    osg
    -0.06
     landmarks
    -0.06
    니다
    -0.06
    人们
    -0.06
     deactivate
    -0.06
    -drive
    -0.06
     อำ
    -0.06
     gehört
    -0.06
    POSITIVE LOGITS
     Kil
    0.06
     quantidade
    0.06
    	es
    0.06
     packed
    0.06
    (hist
    0.06
     Pornhub
    0.06
    บก
    0.06
    фици
    0.06
     linear
    0.06
     ironically
    0.06
    Act Density 0.018%

    No Known Activations