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

    Neuronpedia

    INDEX
    Explanations

    establish choice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     أي
    0.38
    或許
    0.38
    Surgery
    0.38
    歯
    0.37
    vodu
    0.37
     ugg
    0.37
    呈現
    0.36
    這一
    0.36
     ments
    0.36
     échant
    0.36
    POSITIVE LOGITS
    醍
    0.40
    작
    0.38
     increase
    0.36
     sej
    0.36
     substitute
    0.35
     botan
    0.35
     tuj
    0.35
    okinetic
    0.34
     আর্মি
    0.34
     obt
    0.34
    Act Density 0.001%

    No Known Activations