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

    Neuronpedia

    INDEX
    Explanations

    Japanese/Korean particles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     欧美
    -0.06
     pedestal
    -0.06
     podařilo
    -0.06
    зем
    -0.06
    udicots
    -0.06
     bigot
    -0.06
     sức
    -0.06
     дот
    -0.06
    ']."
    -0.06
     Taylor
    -0.06
    POSITIVE LOGITS
    _articles
    0.08
    _article
    0.08
     �
    0.08
    .NO
    0.07
    /common
    0.07
    	I
    0.06
     told
    0.06
     fond
    0.06
     caused
    0.06
     Stafford
    0.06
    Act Density 0.011%

    No Known Activations