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

    Neuronpedia

    INDEX
    Explanations

    generated code classes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     swings
    0.46
     preaching
    0.40
     इंतजार
    0.39
     grunn
    0.38
     આનંદ
    0.37
    働く
    0.37
    ഴ
    0.36
     chim
    0.36
     idha
    0.36
     Sedona
    0.36
    POSITIVE LOGITS
    CodeDom
    0.59
    Generated
    0.57
    AutoGen
    0.55
    DebuggerNonUser
    0.55
    Code
    0.52
    Generator
    0.50
     Generated
    0.49
    代码
    0.49
     производи
    0.49
    Generation
    0.48
    Act Density 0.001%

    No Known Activations