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

    Neuronpedia

    INDEX
    Explanations

    Button server start join client

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    हेलो
    0.36
     conosce
    0.36
     enter
    0.35
     tulis
    0.34
     alamy
    0.34
     ambito
    0.34
     giphy
    0.34
     derece
    0.34
    請
    0.33
     ronde
    0.33
    POSITIVE LOGITS
    áll
    0.41
     Reduces
    0.36
     pollution
    0.35
     الفور
    0.35
    Capital
    0.35
     Installing
    0.35
     Does
    0.34
     Doesn
    0.34
     ทำ
    0.34
     安装
    0.34
    Act Density 0.000%

    No Known Activations