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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    softmax
    -0.07
     `,↵
    -0.07
    比赛
    -0.07
    iqu
    -0.07
    	html
    -0.07
    汇
    -0.06
    ,text
    -0.06
     otherButtonTitles
    -0.06
     opioid
    -0.06
    ]",↵
    -0.06
    POSITIVE LOGITS
     жов
    0.07
     هند
    0.07
     stoi
    0.06
     cand
    0.06
    -len
    0.06
    .Categories
    0.06
     friend
    0.06
     خود
    0.06
     Found
    0.06
    ến
    0.06
    Act Density 0.003%

    No Known Activations