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

    Neuronpedia

    INDEX
    Explanations

    C# code using LINQ and collections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    woman
    0.38
    emaking
    0.38
    joining
    0.37
    soe
    0.37
    ře
    0.36
    óso
    0.36
    炭
    0.36
    ров
    0.35
    要
    0.35
    spinner
    0.35
    POSITIVE LOGITS
    Linq
    0.54
    ComponentModel
    0.41
    Collections
    0.38
     rad
    0.37
     Kusum
    0.36
     diverging
    0.36
     зокрема
    0.34
     Indo
    0.34
     Cinque
    0.34
     Kendra
    0.34
    Act Density 0.000%

    No Known Activations