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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ham
    -0.07
    цев
    -0.07
    battle
    -0.07
    SAFE
    -0.07
    偌
    -0.06
    抵抗
    -0.06
    rier
    -0.06
    Muon
    -0.06
    乃
    -0.06
    不是很
    -0.06
    POSITIVE LOGITS
    -reply
    0.07
     derecho
    0.07
     Additional
    0.07
    plement
    0.07
     hashMap
    0.06
    onomy
    0.06
    צוע
    0.06
    购票
    0.06
     tourism
    0.06
    ,List
    0.06
    Act Density 0.049%

    No Known Activations