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

    Neuronpedia

    INDEX
    Explanations

    Dr. Anya Sharma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🦍
    0.47
    ガチャ
    0.46
    <0x85>
    0.39
    😙
    0.39
    査
    0.38
    😏
    0.38
    ullahi
    0.36
    AuthConfig
    0.36
    igamma
    0.36
     QnrB
    0.36
    POSITIVE LOGITS
     lehetős
    0.34
     prat
    0.34
     transport
    0.34
     આમ
    0.34
     זאת
    0.34
     fulfilled
    0.33
     світу
    0.33
     আবদ্ধ
    0.32
     aloj
    0.32
     nokt
    0.32
    Act Density 0.000%

    No Known Activations