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

    Neuronpedia

    INDEX
    Explanations

    C# code structures like struct, dll, cmd

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kucch
    0.43
    漩
    0.40
    setScene
    0.39
    喃
    0.39
     தாய்
    0.38
     bele
    0.38
    grandchildren
    0.37
     Riley
    0.37
    banam
    0.36
     travailler
    0.36
    POSITIVE LOGITS
     Assembly
    0.61
    DebuggerNonUser
    0.60
     Serializable
    0.59
    assembly
    0.55
    Assembly
    0.54
     assembly
    0.51
     Attributes
    0.50
    Struct
    0.49
    Attributes
    0.49
     Attribute
    0.48
    Act Density 0.003%

    No Known Activations