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

    Neuronpedia

    INDEX
    Explanations

    executive safety suspicious

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     radiation
    0.38
    實
    0.38
     RT
    0.37
     ventilators
    0.37
    RADIATION
    0.36
     fi
    0.36
     fin
    0.36
     conscience
    0.35
     het
    0.35
     ile
    0.35
    POSITIVE LOGITS
     कॉल्ड
    0.42
    oč
    0.41
    余额
    0.40
    穷
    0.40
     वर
    0.40
    资讯
    0.40
     kaçtır
    0.40
    postId
    0.39
    逦
    0.39
     卡
    0.39
    Act Density 0.001%

    No Known Activations