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

    Neuronpedia

    INDEX
    Explanations

    installation instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ingleton
    0.53
     titel
    0.41
     เหตุ
    0.41
    ."),
    0.41
    🚔
    0.41
     አሉ
    0.40
     hinzufügen
    0.40
     प्
    0.40
     Visible
    0.40
     visibly
    0.39
    POSITIVE LOGITS
    仿
    0.46
    Models
    0.39
    Visitor
    0.38
    Toyota
    0.38
    完整
    0.37
    罕
    0.37
     frust
    0.36
     gây
    0.36
    Museum
    0.36
    Zn
    0.36
    Act Density 0.215%

    No Known Activations